{"version":"1.0","encoding":"UTF-8","feed":{"xmlns":"http://www.w3.org/2005/Atom","xmlns$openSearch":"http://a9.com/-/spec/opensearchrss/1.0/","xmlns$blogger":"http://schemas.google.com/blogger/2008","xmlns$georss":"http://www.georss.org/georss","xmlns$gd":"http://schemas.google.com/g/2005","xmlns$thr":"http://purl.org/syndication/thread/1.0","id":{"$t":"tag:blogger.com,1999:blog-3214439820919958302"},"updated":{"$t":"2026-03-20T16:01:49.616+08:00"},"category":[{"term":"*jour*"},{"term":"text-analysis"},{"term":"textual-emotion-analysis"},{"term":"*conf*"},{"term":"sentiment-analysis"},{"term":"clustering"},{"term":"emotion-analysis"},{"term":"lexicon"},{"term":"deep-learning"},{"term":"lexicon-construction"},{"term":"emotion-detection"},{"term":"emotion-lexicon"},{"term":"topic-modeling"},{"term":"neural"},{"term":"survey"},{"term":"dimensionality-reduction"},{"term":"supervised-learning"},{"term":"unsupervised-learning"},{"term":"convolutional"},{"term":"k-means"},{"term":"*blog*"},{"term":"sentiment-lexicon"},{"term":"feature-extraction"},{"term":"long-short-term-memory"},{"term":"politics"},{"term":"adjective"},{"term":"seed-lexicon"},{"term":"twitter"},{"term":"embedding"},{"term":"emotion-lexicon-construction"},{"term":"n-gram"},{"term":"adverb"},{"term":"attention"},{"term":"fuzzy"},{"term":"fuzzy-c-means"},{"term":"subspace-clustering"},{"term":"text-classification"},{"term":"BERT"},{"term":"JS"},{"term":"ML"},{"term":"MLJS"},{"term":"covid-19"},{"term":"emoticon"},{"term":"fake-news"},{"term":"fuzzy-clustering"},{"term":"gated-recurrent-unit"},{"term":"healthcare"},{"term":"noun"},{"term":"sentiment-clustering"},{"term":"social-media"},{"term":"stemming"},{"term":"task-analysis"},{"term":"verb"},{"term":"Information-science"},{"term":"analytical-model"},{"term":"annotation"},{"term":"artificial-neural"},{"term":"aspect"},{"term":"blog"},{"term":"c-means"},{"term":"co-occurence"},{"term":"corpus-based"},{"term":"data model"},{"term":"deep-averaging"},{"term":"denoising-autoencoders"},{"term":"disaster"},{"term":"education"},{"term":"emoji"},{"term":"feature-selection"},{"term":"financial"},{"term":"fraud-detection"},{"term":"h"},{"term":"hate-speech"},{"term":"hybrid"},{"term":"indexes"},{"term":"latent-dirichlet-allocation"},{"term":"lexicon-embedding"},{"term":"logistics"},{"term":"low-resource language"},{"term":"machine translation"},{"term":"multi-head-attention"},{"term":"negation-word"},{"term":"nlp-model"},{"term":"opinion-mining"},{"term":"pointwise-mutual-information"},{"term":"polar-word"},{"term":"prompt-based learning"},{"term":"pruning-technique"},{"term":"recurrent"},{"term":"seed-words"},{"term":"semantic-similarity"},{"term":"short-text"},{"term":"social-networking"},{"term":"spam-detection"},{"term":"support-vector-machines"},{"term":"text-mining"},{"term":"tf-idf"},{"term":"toxicity"},{"term":"transfer-learning"},{"term":"vaccine"},{"term":"vector"},{"term":"vocabulary"},{"term":"wisdom-of-crowd"},{"term":"word-association"},{"term":"word2vec"}],"title":{"type":"text","$t":"Mahmood"},"subtitle":{"type":"html","$t":"Textual Emotion Analysis"},"link":[{"rel":"http://schemas.google.com/g/2005#feed","type":"application/atom+xml","href":"https:\/\/mahmood.razzi.my\/feeds\/posts\/default"},{"rel":"self","type":"application/atom+xml","href":"https:\/\/www.blogger.com\/feeds\/3214439820919958302\/posts\/default?alt=json\u0026max-results=500\u0026q=%5Bdeep-learning%5D"},{"rel":"alternate","type":"text/html","href":"https:\/\/mahmood.razzi.my\/"},{"rel":"hub","href":"http://pubsubhubbub.appspot.com/"}],"author":[{"name":{"$t":"admin"},"uri":{"$t":"http:\/\/www.blogger.com\/profile\/06798775486136938230"},"email":{"$t":"noreply@blogger.com"},"gd$image":{"rel":"http://schemas.google.com/g/2005#thumbnail","width":"16","height":"16","src":"https:\/\/img1.blogblog.com\/img\/b16-rounded.gif"}}],"generator":{"version":"7.00","uri":"http://www.blogger.com","$t":"Blogger"},"openSearch$totalResults":{"$t":"35"},"openSearch$startIndex":{"$t":"1"},"openSearch$itemsPerPage":{"$t":"500"},"entry":[{"id":{"$t":"tag:blogger.com,1999:blog-3214439820919958302.post-2143126507302866090"},"published":{"$t":"2023-03-01T14:24:00.005+08:00"},"updated":{"$t":"2023-03-01T14:24:00.175+08:00"},"category":[{"scheme":"http://www.blogger.com/atom/ns#","term":"*jour*"},{"scheme":"http://www.blogger.com/atom/ns#","term":"education"},{"scheme":"http://www.blogger.com/atom/ns#","term":"sentiment-analysis"},{"scheme":"http://www.blogger.com/atom/ns#","term":"text-analysis"}],"title":{"type":"text","$t":"Sentiment analysis and opinion mining on educational data: A survey"},"content":{"type":"html","$t":"\u003Cp\u003E***\u003C\/p\u003E\u003Cp\u003EAbstract:\u003C\/p\u003E\u003Cp\u003ESentiment analysis AKA opinion mining is one of the most widely used NLP applications to identify human intentions from their reviews.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EIn the education sector, opinion mining is used to listen to student opinions and enhance their learning–teaching practices pedagogically.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EWith advancements in sentiment annotation techniques and AI methodologies, student comments can be labelled with their sentiment orientation without much human intervention.​\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EIn this review article, (1) we consider the role of emotional analysis in education from four levels: document level, sentence level, entity level, and aspect level, (2) sentiment annotation techniques including lexicon-based and corpus-based approaches for unsupervised annotations are explored, (3) the role of AI in sentiment analysis with methodologies like machine learning, deep learning, and transformers are discussed, (4) the impact of sentiment analysis on educational procedures to enhance pedagogy, decision-making, and evaluation are presented.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EEducational institutions have been widely invested to build sentiment analysis tools and process their student feedback to draw their opinions and insights.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EApplications built on sentiment analysis of student feedback are reviewed in this study.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EChallenges in sentiment analysis like multi-polarity, polysemous, negation words, and opinion spam detection are explored and their trends in the research space are discussed.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EThe future directions of sentiment analysis in education are discussed.\u003C\/p\u003E\u003Cp\u003E***\u0026nbsp;\u003C\/p\u003E\u003Cp\u003E\u003Ca href=\"https:\/\/www.sciencedirect.com\/science\/article\/pii\/S2949719122000036\"\u003Ehttps:\/\/www.sciencedirect.com\/science\/article\/pii\/S2949719122000036\u003C\/a\u003E\u003C\/p\u003E\u003Cp\u003E***\u003C\/p\u003E"},"link":[{"rel":"replies","type":"application/atom+xml","href":"https:\/\/mahmood.razzi.my\/feeds\/2143126507302866090\/comments\/default","title":"Post Comments"},{"rel":"replies","type":"text/html","href":"https:\/\/www.blogger.com\/comment\/fullpage\/post\/3214439820919958302\/2143126507302866090","title":"0 Comments"},{"rel":"edit","type":"application/atom+xml","href":"https:\/\/www.blogger.com\/feeds\/3214439820919958302\/posts\/default\/2143126507302866090"},{"rel":"self","type":"application/atom+xml","href":"https:\/\/www.blogger.com\/feeds\/3214439820919958302\/posts\/default\/2143126507302866090"},{"rel":"alternate","type":"text/html","href":"https:\/\/mahmood.razzi.my\/2023\/03\/sentiment-analysis-and-opinion-mining.html","title":"Sentiment analysis and opinion mining on educational data: A survey"}],"author":[{"name":{"$t":"Unknown"},"email":{"$t":"noreply@blogger.com"},"gd$image":{"rel":"http://schemas.google.com/g/2005#thumbnail","width":"16","height":"16","src":"https:\/\/img1.blogblog.com\/img\/b16-rounded.gif"}}],"thr$total":{"$t":"0"}},{"id":{"$t":"tag:blogger.com,1999:blog-3214439820919958302.post-5423379890958271463"},"published":{"$t":"2022-11-21T15:56:00.004+08:00"},"updated":{"$t":"2023-01-23T15:59:00.994+08:00"},"category":[{"scheme":"http://www.blogger.com/atom/ns#","term":"*jour*"},{"scheme":"http://www.blogger.com/atom/ns#","term":"aspect"},{"scheme":"http://www.blogger.com/atom/ns#","term":"text-analysis"}],"title":{"type":"text","$t":"A Survey on Aspect-Based Sentiment Classification"},"content":{"type":"html","$t":"\u003Cp\u003E***\u003C\/p\u003E\u003Cp\u003EAbstract:\u003C\/p\u003E\u003Cp\u003EWith the constantly growing number of reviews and other sentiment-bearing texts on the Web, the demand for automatic sentiment analysis algorithms continues to expand.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EAspect-based sentiment classification (ABSC) allows for the automatic extraction of highly fine-grained sentiment information from text documents or sentences.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EIn this survey, the rapidly evolving state of the research on ABSC is reviewed.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EA novel taxonomy is proposed that categorizes the ABSC models into three major categories: knowledge-based, machine learning, and hybrid models.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EThis taxonomy is accompanied with summarizing overviews of the reported model performances, and both technical and intuitive explanations of the various ABSC models.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EState-of-the-art ABSC models are discussed, such as models based on the transformer model, and hybrid deep learning models that incorporate knowledge bases.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EAdditionally, various techniques for representing the model inputs and evaluating the model outputs are reviewed.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EFurthermore, trends in the research on ABSC are identified and a discussion is provided on the ways in which the field of ABSC can be advanced in the future.\u003C\/p\u003E\u003Cp\u003E***\u0026nbsp;\u003C\/p\u003E\u003Cp\u003E\u003Ca href=\"https:\/\/dl.acm.org\/doi\/10.1145\/3503044\"\u003Ehttps:\/\/dl.acm.org\/doi\/10.1145\/3503044\u003C\/a\u003E\u003C\/p\u003E\u003Cp\u003E\u003Ca href=\"https:\/\/arxiv.org\/pdf\/2203.01054.pdf\"\u003Ehttps:\/\/arxiv.org\/pdf\/2203.01054.pdf\u003C\/a\u003E\u003C\/p\u003E\u003Cp\u003E***\u003C\/p\u003E"},"link":[{"rel":"replies","type":"application/atom+xml","href":"https:\/\/mahmood.razzi.my\/feeds\/5423379890958271463\/comments\/default","title":"Post Comments"},{"rel":"replies","type":"text/html","href":"https:\/\/www.blogger.com\/comment\/fullpage\/post\/3214439820919958302\/5423379890958271463","title":"0 Comments"},{"rel":"edit","type":"application/atom+xml","href":"https:\/\/www.blogger.com\/feeds\/3214439820919958302\/posts\/default\/5423379890958271463"},{"rel":"self","type":"application/atom+xml","href":"https:\/\/www.blogger.com\/feeds\/3214439820919958302\/posts\/default\/5423379890958271463"},{"rel":"alternate","type":"text/html","href":"https:\/\/mahmood.razzi.my\/2022\/11\/a-survey-on-aspect-based-sentiment.html","title":"A Survey on Aspect-Based Sentiment Classification"}],"author":[{"name":{"$t":"Unknown"},"email":{"$t":"noreply@blogger.com"},"gd$image":{"rel":"http://schemas.google.com/g/2005#thumbnail","width":"16","height":"16","src":"https:\/\/img1.blogblog.com\/img\/b16-rounded.gif"}}],"thr$total":{"$t":"0"}},{"id":{"$t":"tag:blogger.com,1999:blog-3214439820919958302.post-7678822478287938481"},"published":{"$t":"2022-10-14T01:45:00.007+08:00"},"updated":{"$t":"2023-01-22T12:50:45.046+08:00"},"category":[{"scheme":"http://www.blogger.com/atom/ns#","term":"*jour*"},{"scheme":"http://www.blogger.com/atom/ns#","term":"attention"},{"scheme":"http://www.blogger.com/atom/ns#","term":"convolutional"},{"scheme":"http://www.blogger.com/atom/ns#","term":"deep-averaging"},{"scheme":"http://www.blogger.com/atom/ns#","term":"denoising-autoencoders"},{"scheme":"http://www.blogger.com/atom/ns#","term":"gated-recurrent-unit"},{"scheme":"http://www.blogger.com/atom/ns#","term":"long-short-term-memory"},{"scheme":"http://www.blogger.com/atom/ns#","term":"multi-head-attention"},{"scheme":"http://www.blogger.com/atom/ns#","term":"recurrent"},{"scheme":"http://www.blogger.com/atom/ns#","term":"text-analysis"},{"scheme":"http://www.blogger.com/atom/ns#","term":"textual-emotion-analysis"}],"title":{"type":"text","$t":"A survey on deep learning for textual emotion analysis in social networks"},"content":{"type":"html","$t":"\u003Cp\u003E\u0026nbsp;***\u003C\/p\u003E\u003Cp\u003EAbstract\u003C\/p\u003E\u003Cp\u003ETextual Emotion Analysis (TEA) aims to extract and analyze user emotional states in texts.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EVarious Deep Learning (DL) methods have developed rapidly, and they have proven to be successful in many fields such as audio, image, and natural language processing.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EThis trend has drawn increasing researchers away from traditional machine learning to DL for their scientific research.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EIn this paper, we provide an overview on TEA based on DL methods.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EAfter introducing a background for emotion analysis that includes defining emotion, emotion classification methods, and application domains of emotion analysis, we summarize DL technology, and the word\/sentence representation learning method.\u003C\/p\u003E\u003Cp\u003EWe then categorize existing TEA methods based on text structures and linguistic types: text-oriented monolingual methods, text conversations-oriented monolingual methods, text-oriented cross-linguistic methods, and emoji-oriented cross-linguistic methods.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EWe close by discussing emotion analysis challenges and future research trends.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EWe hope that our survey will assist interested readers in understanding the relationship between TEA and DL methods while also improving TEA development.\u003C\/p\u003E\u003Cp\u003E***\u003C\/p\u003E\u003Cp\u003EKeywords\u003C\/p\u003E\u003Cp\u003EText Emotion analysis Deep learning Sentiment analysis Pre-training\u003C\/p\u003E\u003Cp\u003E***\u003C\/p\u003E\u003Cp\u003E\u003Ca href=\"https:\/\/doi.org\/10.1016\/j.dcan.2021.10.003\"\u003Ehttps:\/\/doi.org\/10.1016\/j.dcan.2021.10.003\u003C\/a\u003E\u003C\/p\u003E\u003Cp\u003E\u003Ca href=\"https:\/\/www.sciencedirect.com\/science\/article\/pii\/S2352864821000833\"\u003Ehttps:\/\/www.sciencedirect.com\/science\/article\/pii\/S2352864821000833\u003C\/a\u003E\u003C\/p\u003E\u003Cp\u003E\u003Ca href=\"https:\/\/www.semanticscholar.org\/paper\/A-survey-on-deep-learning-for-textual-emotion-in-Peng-Cao\/537f965cb83ed92b1aa51bb20fcbddc9ce1be26f\"\u003Ehttps:\/\/www.semanticscholar.org\/paper\/A-survey-on-deep-learning-for-textual-emotion-in-Peng-Cao\/537f965cb83ed92b1aa51bb20fcbddc9ce1be26f\u003C\/a\u003E)\u003C\/p\u003E\u003Cp\u003E***\u003C\/p\u003E\u003Cp\u003E\u003Cbr \/\u003E\u003C\/p\u003E"},"link":[{"rel":"replies","type":"application/atom+xml","href":"https:\/\/mahmood.razzi.my\/feeds\/7678822478287938481\/comments\/default","title":"Post Comments"},{"rel":"replies","type":"text/html","href":"https:\/\/www.blogger.com\/comment\/fullpage\/post\/3214439820919958302\/7678822478287938481","title":"0 Comments"},{"rel":"edit","type":"application/atom+xml","href":"https:\/\/www.blogger.com\/feeds\/3214439820919958302\/posts\/default\/7678822478287938481"},{"rel":"self","type":"application/atom+xml","href":"https:\/\/www.blogger.com\/feeds\/3214439820919958302\/posts\/default\/7678822478287938481"},{"rel":"alternate","type":"text/html","href":"https:\/\/mahmood.razzi.my\/2022\/10\/a-survey-on-deep-learning-for-textual.html","title":"A survey on deep learning for textual emotion analysis in social networks"}],"author":[{"name":{"$t":"Unknown"},"email":{"$t":"noreply@blogger.com"},"gd$image":{"rel":"http://schemas.google.com/g/2005#thumbnail","width":"16","height":"16","src":"https:\/\/img1.blogblog.com\/img\/b16-rounded.gif"}}],"thr$total":{"$t":"0"}},{"id":{"$t":"tag:blogger.com,1999:blog-3214439820919958302.post-4164287105112643405"},"published":{"$t":"2022-09-27T01:36:00.006+08:00"},"updated":{"$t":"2023-01-22T13:02:11.688+08:00"},"category":[{"scheme":"http://www.blogger.com/atom/ns#","term":"*jour*"},{"scheme":"http://www.blogger.com/atom/ns#","term":"pointwise-mutual-information"},{"scheme":"http://www.blogger.com/atom/ns#","term":"seed-lexicon"},{"scheme":"http://www.blogger.com/atom/ns#","term":"text-analysis"},{"scheme":"http://www.blogger.com/atom/ns#","term":"textual-emotion-analysis"},{"scheme":"http://www.blogger.com/atom/ns#","term":"word2vec"}],"title":{"type":"text","$t":"A Deep Learning-Based Text Emotional Analysis Framework for Yellow River Basin Tourism Culture"},"content":{"type":"html","$t":"\u003Cp\u003E***\u003C\/p\u003E\u003Cp\u003EAbstract:\u003C\/p\u003E\u003Cp\u003EAs an important carrier of cultural communication, tourism can play a positive role in promoting regional ecology and cultural heritage.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003ETherefore, this paper takes tourist attractions in the Yellow River basin as the research object and constructs mining and comment sentiment analysis for tourism text information in the Yellow River basin that appears on social media platforms.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EBased on the theory of the social center network, the tourism culture network of the Yellow River basin based on tourists’ emotion analysis is constructed.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EIn addition, based on the linear fusion algorithm of semantic orientation pointwise mutual information and word2vec, this paper constructs an emotion dictionary in the field of tourism review and proposes a set of comprehensive emotion calculation rules based on Chinese text expression structure.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EThe experimental results of 32 scenic spots in the Yellow River basin show that the proposed algorithm can achieve better sentiment classification of tourism texts, broaden the scope of application of the domain sentiment dictionary construction method, and improve efficiency.\u003C\/p\u003E\u003Cp\u003E***\u0026nbsp;\u003C\/p\u003E\u003Cp\u003E\u003Ca href=\"https:\/\/www.hindawi.com\/journals\/misy\/2022\/6836223\/\"\u003Ehttps:\/\/www.hindawi.com\/journals\/misy\/2022\/6836223\/\u003C\/a\u003E\u003C\/p\u003E\u003Cp\u003E\u003Ca href=\"https:\/\/downloads.hindawi.com\/journals\/misy\/2022\/6836223.pdf\"\u003Ehttps:\/\/downloads.hindawi.com\/journals\/misy\/2022\/6836223.pdf\u003C\/a\u003E\u003C\/p\u003E\u003Cp\u003E***\u003C\/p\u003E"},"link":[{"rel":"replies","type":"application/atom+xml","href":"https:\/\/mahmood.razzi.my\/feeds\/4164287105112643405\/comments\/default","title":"Post Comments"},{"rel":"replies","type":"text/html","href":"https:\/\/www.blogger.com\/comment\/fullpage\/post\/3214439820919958302\/4164287105112643405","title":"0 Comments"},{"rel":"edit","type":"application/atom+xml","href":"https:\/\/www.blogger.com\/feeds\/3214439820919958302\/posts\/default\/4164287105112643405"},{"rel":"self","type":"application/atom+xml","href":"https:\/\/www.blogger.com\/feeds\/3214439820919958302\/posts\/default\/4164287105112643405"},{"rel":"alternate","type":"text/html","href":"https:\/\/mahmood.razzi.my\/2022\/09\/a-deep-learning-based-text-emotional.html","title":"A Deep Learning-Based Text Emotional Analysis Framework for Yellow River Basin Tourism Culture"}],"author":[{"name":{"$t":"Unknown"},"email":{"$t":"noreply@blogger.com"},"gd$image":{"rel":"http://schemas.google.com/g/2005#thumbnail","width":"16","height":"16","src":"https:\/\/img1.blogblog.com\/img\/b16-rounded.gif"}}],"thr$total":{"$t":"0"}},{"id":{"$t":"tag:blogger.com,1999:blog-3214439820919958302.post-1336839342941014872"},"published":{"$t":"2022-08-23T21:48:00.008+08:00"},"updated":{"$t":"2023-01-22T12:52:09.067+08:00"},"category":[{"scheme":"http://www.blogger.com/atom/ns#","term":"*jour*"},{"scheme":"http://www.blogger.com/atom/ns#","term":"convolutional"},{"scheme":"http://www.blogger.com/atom/ns#","term":"deep-learning"},{"scheme":"http://www.blogger.com/atom/ns#","term":"gated-recurrent-unit"},{"scheme":"http://www.blogger.com/atom/ns#","term":"textual-emotion-analysis"}],"title":{"type":"text","$t":"Text-Based Emotion Recognition Using Deep Learning Approach"},"content":{"type":"html","$t":"\u003Cp\u003E***\u003C\/p\u003E\u003Cp\u003EAbstract:\u003C\/p\u003E\u003Cp\u003ESentiment analysis is a method to identify people's attitudes, sentiments, and emotions towards a given goal, such as people, activities, organizations, services, subjects, and products.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EEmotion detection is a subset of sentiment analysis as it predicts the unique emotion rather than just stating positive, negative, or neutral.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EIn recent times, many researchers have already worked on speech and facial expressions for emotion recognition.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EHowever, emotion detection in text is a tedious task as cues are missing, unlike in speech, such as tonal stress, facial expression, pitch, etc.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003ETo identify emotions from text, several methods have been proposed in the past using natural language processing (NLP) techniques: the keyword approach, the lexicon-based approach, and the machine learning approach.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EHowever, there were some limitations with keyword- and lexicon-based approaches as they focus on semantic relations.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EIn this article, we have proposed a hybrid (machine learning + deep learning) model to identify emotions in text.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EConvolutional neural network (CNN) and Bi-GRU were exploited as deep learning techniques.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003ESupport vector machine is used as a machine learning approach.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EThe performance of the proposed approach is evaluated using a combination of three different types of datasets, namely, sentences, tweets, and dialogs, and it attains an accuracy of 80.11%.\u003C\/p\u003E\u003Cp\u003E***\u003C\/p\u003E\u003Cp\u003E\u003Ca href=\"https:\/\/www.ncbi.nlm.nih.gov\/pmc\/articles\/PMC9427219\/\"\u003Ehttps:\/\/www.ncbi.nlm.nih.gov\/pmc\/articles\/PMC9427219\/\u003C\/a\u003E\u003C\/p\u003E\u003Cp\u003E***\u003C\/p\u003E\u003Cp\u003E\u003Cbr \/\u003E\u003C\/p\u003E\u003Cp\u003E***\u0026nbsp;\u003C\/p\u003E"},"link":[{"rel":"replies","type":"application/atom+xml","href":"https:\/\/mahmood.razzi.my\/feeds\/1336839342941014872\/comments\/default","title":"Post Comments"},{"rel":"replies","type":"text/html","href":"https:\/\/www.blogger.com\/comment\/fullpage\/post\/3214439820919958302\/1336839342941014872","title":"0 Comments"},{"rel":"edit","type":"application/atom+xml","href":"https:\/\/www.blogger.com\/feeds\/3214439820919958302\/posts\/default\/1336839342941014872"},{"rel":"self","type":"application/atom+xml","href":"https:\/\/www.blogger.com\/feeds\/3214439820919958302\/posts\/default\/1336839342941014872"},{"rel":"alternate","type":"text/html","href":"https:\/\/mahmood.razzi.my\/2022\/08\/text-based-emotion-recognition-using.html","title":"Text-Based Emotion Recognition Using Deep Learning Approach"}],"author":[{"name":{"$t":"Unknown"},"email":{"$t":"noreply@blogger.com"},"gd$image":{"rel":"http://schemas.google.com/g/2005#thumbnail","width":"16","height":"16","src":"https:\/\/img1.blogblog.com\/img\/b16-rounded.gif"}}],"thr$total":{"$t":"0"}},{"id":{"$t":"tag:blogger.com,1999:blog-3214439820919958302.post-3906386273282601928"},"published":{"$t":"2022-08-04T06:38:00.003+08:00"},"updated":{"$t":"2023-01-21T01:31:08.102+08:00"},"category":[{"scheme":"http://www.blogger.com/atom/ns#","term":"*jour*"},{"scheme":"http://www.blogger.com/atom/ns#","term":"covid-19"},{"scheme":"http://www.blogger.com/atom/ns#","term":"opinion-mining"},{"scheme":"http://www.blogger.com/atom/ns#","term":"social-media"},{"scheme":"http://www.blogger.com/atom/ns#","term":"twitter"},{"scheme":"http://www.blogger.com/atom/ns#","term":"vaccine"}],"title":{"type":"text","$t":"The Longest Month: Analyzing COVID-19 Vaccination Opinions Dynamics From Tweets in the Month Following the First Vaccine Announcement"},"content":{"type":"html","$t":"\u003Cp\u003E\u0026nbsp;***\u003C\/p\u003E\u003Cp\u003EAbstract:\u003C\/p\u003E\u003Cp\u003EThe coronavirus outbreak has brought unprecedented measures, which forced the authorities to make decisions related to the instauration of lockdowns in the areas most hit by the pandemic.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003ESocial media has been an important support for people while passing through this difficult period.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EOn November 9, 2020, when the first vaccine with more than 90% effective rate has been announced, the social media has reacted and people worldwide have started to express their feelings related to the vaccination, which was no longer a hypothesis but closer, each day, to become a reality.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EThe present paper aims to analyze the dynamics of the opinions regarding COVID-19 vaccination by considering the one-month period following the first vaccine announcement, until the first vaccination took place in UK, in which the civil society has manifested a higher interest regarding the vaccination process.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EClassical machine learning and deep learning algorithms have been compared to select the best performing classifier.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003E2 349 659 tweets have been collected, analyzed, and put in connection with the events reported by the media.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EBased on the analysis, it can be observed that most of the tweets have a neutral stance, while the number of in favor tweets overpasses the number of against tweets.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EAs for the news, it has been observed that the occurrence of tweets follows the trend of the events.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EEven more, the proposed approach can be used for a longer monitoring campaign that can help the governments to create appropriate means of communication and to evaluate them in order to provide clear and adequate information to the general public, which could increase the public trust in a vaccination campaign.\u003C\/p\u003E\u003Cp\u003E***\u003C\/p\u003E\u003Cp\u003EKeywords: Opinion mining, social media, COVID-19, SARS-CoV-2, stance classification, vaccine\u003C\/p\u003E\u003Cp\u003E***\u003C\/p\u003E\u003Cp\u003EP:(\u003Ca href=\"https:\/\/ieeexplore.ieee.org\/document\/9354776\"\u003Ehttps:\/\/ieeexplore.ieee.org\/document\/9354776\u003C\/a\u003E)\u003C\/p\u003E\u003Cp\u003ES:(\u003Ca href=\"https:\/\/www.semanticscholar.org\/paper\/The-Longest-Month%3A-Analyzing-COVID-19-Vaccination-Cotfas-Delcea\/32cd4caddc7799050d2e5594eee3af7160676412\"\u003Ehttps:\/\/www.semanticscholar.org\/paper\/The-Longest-Month%3A-Analyzing-COVID-19-Vaccination-Cotfas-Delcea\/32cd4caddc7799050d2e5594eee3af7160676412\u003C\/a\u003E)\u003C\/p\u003E\u003Cp\u003ED:(\u003Ca href=\"https:\/\/ieeexplore.ieee.org\/ielx7\/6287639\/9312710\/09354776.pdf\"\u003Ehttps:\/\/ieeexplore.ieee.org\/ielx7\/6287639\/9312710\/09354776.pdf\u003C\/a\u003E)\u003C\/p\u003E\u003Cp\u003E[twitter]\u003C\/p\u003E\u003Cp\u003E***\u003C\/p\u003E"},"link":[{"rel":"replies","type":"application/atom+xml","href":"https:\/\/mahmood.razzi.my\/feeds\/3906386273282601928\/comments\/default","title":"Post Comments"},{"rel":"replies","type":"text/html","href":"https:\/\/www.blogger.com\/comment\/fullpage\/post\/3214439820919958302\/3906386273282601928","title":"0 Comments"},{"rel":"edit","type":"application/atom+xml","href":"https:\/\/www.blogger.com\/feeds\/3214439820919958302\/posts\/default\/3906386273282601928"},{"rel":"self","type":"application/atom+xml","href":"https:\/\/www.blogger.com\/feeds\/3214439820919958302\/posts\/default\/3906386273282601928"},{"rel":"alternate","type":"text/html","href":"https:\/\/mahmood.razzi.my\/2022\/08\/the-longest-month-analyzing-covid-19.html","title":"The Longest Month: Analyzing COVID-19 Vaccination Opinions Dynamics From Tweets in the Month Following the First Vaccine Announcement"}],"author":[{"name":{"$t":"Unknown"},"email":{"$t":"noreply@blogger.com"},"gd$image":{"rel":"http://schemas.google.com/g/2005#thumbnail","width":"16","height":"16","src":"https:\/\/img1.blogblog.com\/img\/b16-rounded.gif"}}],"thr$total":{"$t":"0"}},{"id":{"$t":"tag:blogger.com,1999:blog-3214439820919958302.post-6248242794246216392"},"published":{"$t":"2022-07-19T20:38:00.001+08:00"},"updated":{"$t":"2023-02-09T20:44:00.312+08:00"},"category":[{"scheme":"http://www.blogger.com/atom/ns#","term":"*blog*"},{"scheme":"http://www.blogger.com/atom/ns#","term":"clustering"}],"title":{"type":"text","$t":"What is Clustering?"},"content":{"type":"html","$t":"\u003Cp\u003E***\u003C\/p\u003E\u003Cp\u003EWhen you're trying to learn about something, say music, one approach might be to look for meaningful groups or collections.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EYou might organize music by genre, while your friend might organize music by decade.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EHow you choose to group items helps you to understand more about them as individual pieces of music.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EYou might find that you have a deep affinity for punk rock and further break down the genre into different approaches or music from different locations.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EOn the other hand, your friend might look at music from the 1980's and be able to understand how the music across genres at that time was influenced by the sociopolitical climate.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EIn both cases, you and your friend have learned something interesting about music, even though you took different approaches.\u003C\/p\u003E\u003Cp\u003EIn machine learning too, we often group examples as a first step to understand a subject (data set) in a machine learning system.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EGrouping unlabeled examples is called clustering.\u003C\/p\u003E\u003Cp\u003EAs the examples are unlabeled, clustering relies on unsupervised machine learning.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EIf the examples are labeled, then clustering becomes classification.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EFor a more detailed discussion of supervised and unsupervised methods see Introduction to Machine Learning Problem Framing.\u003C\/p\u003E\u003Cp\u003E\u003Cimg alt=\"A graph displaying three clusters\" src=\"https:\/\/developers.google.com\/static\/machine-learning\/clustering\/images\/ClusterUnlabeled.png\" style=\"background-color: white; border: 0px; box-sizing: inherit; color: #202124; font-family: Roboto, \u0026quot;Noto Sans\u0026quot;, \u0026quot;Noto Sans JP\u0026quot;, \u0026quot;Noto Sans KR\u0026quot;, \u0026quot;Noto Naskh Arabic\u0026quot;, \u0026quot;Noto Sans Thai\u0026quot;, \u0026quot;Noto Sans Hebrew\u0026quot;, \u0026quot;Noto Sans Bengali\u0026quot;, sans-serif; font-size: 16px; height: auto; margin: 0px; max-width: 100%; padding: 0px;\" \/\u003E\u003C\/p\u003E\u003Cp\u003EA graph displaying three clusters\u003C\/p\u003E\u003Cp\u003EFigure 1: Unlabeled examples grouped into three clusters.\u003C\/p\u003E\u003Cp\u003EBefore you can group similar examples, you first need to find similar examples.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EYou can measure similarity between examples by combining the examples' feature data into a metric, called a similarity measure.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EWhen each example is defined by one or two features, it's easy to measure similarity.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EFor example, you can find similar books by their authors.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EAs the number of features increases, creating a similarity measure becomes more complex.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EWe'll later see how to create a similarity measure in different scenarios.\u003C\/p\u003E\u003Cp\u003E\u003Cbr \/\u003E\u003C\/p\u003E\u003Cp\u003EWhat are the Uses of Clustering?\u003C\/p\u003E\u003Cp\u003EClustering has a myriad of uses in a variety of industries. Some common applications for clustering include the following:\u003C\/p\u003E\u003Cp\u003E\u003C\/p\u003E\u003Cul style=\"text-align: left;\"\u003E\u003Cli\u003Emarket segmentation\u003C\/li\u003E\u003Cli\u003Esocial network analysis\u003C\/li\u003E\u003Cli\u003Esearch result grouping\u003C\/li\u003E\u003Cli\u003Emedical imaging\u003C\/li\u003E\u003Cli\u003Eimage segmentation\u003C\/li\u003E\u003Cli\u003Eanomaly detection\u003C\/li\u003E\u003C\/ul\u003E\u003Cp\u003E\u003C\/p\u003E\u003Cp\u003EAfter clustering, each cluster is assigned a number called a cluster ID.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003ENow, you can condense the entire feature set for an example into its cluster ID.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003ERepresenting a complex example by a simple cluster ID makes clustering powerful.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EExtending the idea, clustering data can simplify large datasets.\u003C\/p\u003E\u003Cp\u003EFor example, you can group items by different features as demonstrated in the following examples:\u003C\/p\u003E\u003Cblockquote style=\"border: none; margin: 0px 0px 0px 40px; padding: 0px; text-align: left;\"\u003E\u003Cp\u003EExamples\u003C\/p\u003E\u003C\/blockquote\u003E\u003Cblockquote style=\"border: none; margin: 0px 0px 0px 40px; padding: 0px; text-align: left;\"\u003E\u003Cp\u003E\u003C\/p\u003E\u003Cul style=\"text-align: left;\"\u003E\u003Cli\u003EGroup stars by brightness.\u003C\/li\u003E\u003Cli\u003EGroup organisms by genetic information into a taxonomy.\u003C\/li\u003E\u003Cli\u003EGroup documents by topic.\u003C\/li\u003E\u003C\/ul\u003E\u003Cp\u003E\u003C\/p\u003E\u003C\/blockquote\u003E\u003Cp\u003EMachine learning systems can then use cluster IDs to simplify the processing of large datasets.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EThus, clustering’s output serves as feature data for downstream ML systems.\u003C\/p\u003E\u003Cp\u003EAt Google, clustering is used for generalization, data compression, and privacy preservation in products such as YouTube videos, Play apps, and Music tracks.\u003C\/p\u003E\u003Cp\u003EGeneralization\u003C\/p\u003E\u003Cp\u003EWhen some examples in a cluster have missing feature data, you can infer the missing data from other examples in the cluster.\u003C\/p\u003E\u003Cp\u003EExample\u003C\/p\u003E\u003Cp\u003ELess popular videos can be clustered with more popular videos to improve video recommendations.\u003C\/p\u003E\u003Cp\u003EData Compression\u003C\/p\u003E\u003Cp\u003EAs discussed, feature data for all examples in a cluster can be replaced by the relevant cluster ID.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EThis replacement simplifies the feature data and saves storage.\u003C\/p\u003E\u003Cp\u003EThese benefits become significant when scaled to large datasets.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EFurther, machine learning systems can use the cluster ID as input instead of the entire feature dataset.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EReducing the complexity of input data makes the ML model simpler and faster to train.\u003C\/p\u003E\u003Cblockquote style=\"border: none; margin: 0px 0px 0px 40px; padding: 0px; text-align: left;\"\u003E\u003Cp\u003EExample\u003C\/p\u003E\u003C\/blockquote\u003E\u003Cblockquote style=\"border: none; margin: 0px 0px 0px 40px; padding: 0px; text-align: left;\"\u003E\u003Cp\u003E\u003C\/p\u003E\u003Cul style=\"text-align: left;\"\u003E\u003Cli\u003EFeature data for a single YouTube video can include:\u003C\/li\u003E\u003Cli\u003Eviewer data on location, time, and demographics\u003C\/li\u003E\u003Cli\u003Ecomment data with timestamps, text, and user IDs\u003C\/li\u003E\u003Cli\u003Evideo tags\u003C\/li\u003E\u003C\/ul\u003E\u003Cp\u003E\u003C\/p\u003E\u003C\/blockquote\u003E\u003Cp\u003EClustering YouTube videos lets you replace this set of features with a single cluster ID, thus compressing your data.\u003C\/p\u003E\u003Cp\u003E\u003Cbr \/\u003E\u003C\/p\u003E\u003Cp\u003E***\u0026nbsp;\u003C\/p\u003E\u003Cp\u003E\u003Ca href=\"https:\/\/developers.google.com\/machine-learning\/clustering\/overview\"\u003Ehttps:\/\/developers.google.com\/machine-learning\/clustering\/overview\u003C\/a\u003E\u003C\/p\u003E\u003Cp\u003E***\u003C\/p\u003E"},"link":[{"rel":"replies","type":"application/atom+xml","href":"https:\/\/mahmood.razzi.my\/feeds\/6248242794246216392\/comments\/default","title":"Post Comments"},{"rel":"replies","type":"text/html","href":"https:\/\/www.blogger.com\/comment\/fullpage\/post\/3214439820919958302\/6248242794246216392","title":"0 Comments"},{"rel":"edit","type":"application/atom+xml","href":"https:\/\/www.blogger.com\/feeds\/3214439820919958302\/posts\/default\/6248242794246216392"},{"rel":"self","type":"application/atom+xml","href":"https:\/\/www.blogger.com\/feeds\/3214439820919958302\/posts\/default\/6248242794246216392"},{"rel":"alternate","type":"text/html","href":"https:\/\/mahmood.razzi.my\/2022\/07\/what-is-clustering_19.html","title":"What is Clustering?"}],"author":[{"name":{"$t":"Unknown"},"email":{"$t":"noreply@blogger.com"},"gd$image":{"rel":"http://schemas.google.com/g/2005#thumbnail","width":"16","height":"16","src":"https:\/\/img1.blogblog.com\/img\/b16-rounded.gif"}}],"thr$total":{"$t":"0"}},{"id":{"$t":"tag:blogger.com,1999:blog-3214439820919958302.post-4661959228559847729"},"published":{"$t":"2022-07-03T20:31:00.001+08:00"},"updated":{"$t":"2023-01-21T20:34:19.436+08:00"},"category":[{"scheme":"http://www.blogger.com/atom/ns#","term":"*jour*"},{"scheme":"http://www.blogger.com/atom/ns#","term":"survey"},{"scheme":"http://www.blogger.com/atom/ns#","term":"textual-emotion-analysis"}],"title":{"type":"text","$t":"Textual Emotion Detection Approaches: a Survey"},"content":{"type":"html","$t":"\u003Cp\u003E***\u003C\/p\u003E\u003Cp\u003EAbstract:\u003C\/p\u003E\u003Cp\u003EOver the past decades, social media attracted individuals to express their feelings on any topic or item, resulting in an incremental growth in the size of created data.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EThese feelings and unstructured data paved the path for business organizations to gather information and build statistical analysis.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EVarious machine learning and natural language processing-based approaches are used for sentiment and emotion analysis.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EMoreover, deep learning-based approaches recently gained popularity due to their remarkable performance in text analysis.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EThis paper provides a comprehensive overview of the prominent machine learning models applied in emotion analysis.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EIt explores various emotion analysis taxonomies, in addition to the constraints of prevalent deep learning architectures.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EThe paper also reviews some of the previously presented contributions in emotion analysis with a focus on deep learning methodologies as well as the most common datasets.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EIt presents a comprehensive comparison between several emotion analysis models.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EThis paper demonstrates the effectiveness of learning-based techniques in tackling emotion analysis challenges.\u003C\/p\u003E\u003Cp\u003E***\u0026nbsp;\u003C\/p\u003E"},"link":[{"rel":"replies","type":"application/atom+xml","href":"https:\/\/mahmood.razzi.my\/feeds\/4661959228559847729\/comments\/default","title":"Post Comments"},{"rel":"replies","type":"text/html","href":"https:\/\/www.blogger.com\/comment\/fullpage\/post\/3214439820919958302\/4661959228559847729","title":"0 Comments"},{"rel":"edit","type":"application/atom+xml","href":"https:\/\/www.blogger.com\/feeds\/3214439820919958302\/posts\/default\/4661959228559847729"},{"rel":"self","type":"application/atom+xml","href":"https:\/\/www.blogger.com\/feeds\/3214439820919958302\/posts\/default\/4661959228559847729"},{"rel":"alternate","type":"text/html","href":"https:\/\/mahmood.razzi.my\/2022\/07\/textual-emotion-detection-approaches.html","title":"Textual Emotion Detection Approaches: a Survey"}],"author":[{"name":{"$t":"Unknown"},"email":{"$t":"noreply@blogger.com"},"gd$image":{"rel":"http://schemas.google.com/g/2005#thumbnail","width":"16","height":"16","src":"https:\/\/img1.blogblog.com\/img\/b16-rounded.gif"}}],"thr$total":{"$t":"0"}},{"id":{"$t":"tag:blogger.com,1999:blog-3214439820919958302.post-3837887429554068999"},"published":{"$t":"2022-06-17T22:33:00.006+08:00"},"updated":{"$t":"2023-02-09T22:37:17.680+08:00"},"category":[{"scheme":"http://www.blogger.com/atom/ns#","term":"*jour*"},{"scheme":"http://www.blogger.com/atom/ns#","term":"sentiment-analysis"},{"scheme":"http://www.blogger.com/atom/ns#","term":"text-analysis"},{"scheme":"http://www.blogger.com/atom/ns#","term":"wisdom-of-crowd"}],"title":{"type":"text","$t":"Crowd Decision Making: Sparse Representation Guided by Sentiment Analysis for Leveraging the Wisdom of the Crowd"},"content":{"type":"html","$t":"\u003Cp\u003E***\u003C\/p\u003E\u003Cp\u003EAbstract:\u003C\/p\u003E\u003Cp\u003EThe “wisdom of the crowd” theory states that a nonexpert crowd makes smarter decisions than a reduced set of experts.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003ESocial network platforms are a source of evaluations in the natural language of any topic, which may be considered as the evaluations of a nonexpert crowd.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EDecision-making (DM) models are constrained by their inability of processing large amounts of evaluations in natural language, as those ones from social networks.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EWe claim that evaluations from social networks can enhance the quality of multiperson multicriteria DM models.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EAccordingly, we propose a crowd DM model guided by sentiment analysis (SA), which solves decision situations leveraging the wisdom of the crowd available in social networks.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EThe model uses several deep-learning SA classification models through opinion triplets to incorporate all the evaluation shades in the DM model.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003ELikewise, the likely lack of information stemmed from the consideration of a large set of users is tackled with a sparse representation of the evaluations.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EWe annotate and release the TripR-2020Large dataset, and we use it to evaluate the model in the use case of restaurant choice.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EThe results show that the integration of the wisdom of the crowd and the different shades of the evaluations enhances the quality of the decision.\u003C\/p\u003E\u003Cp\u003E***\u0026nbsp;\u003C\/p\u003E\u003Cp\u003E\u003Ca href=\"https:\/\/ieeexplore.ieee.org\/document\/9800192\"\u003Ehttps:\/\/ieeexplore.ieee.org\/document\/9800192\u003C\/a\u003E\u003C\/p\u003E\u003Cp\u003E\u003Ca href=\"https:\/\/github.com\/ari-dasci\/OD-TripR-2020Large\"\u003Ehttps:\/\/github.com\/ari-dasci\/OD-TripR-2020Large\u003C\/a\u003E\u003C\/p\u003E\u003Cp\u003E***\u003C\/p\u003E"},"link":[{"rel":"replies","type":"application/atom+xml","href":"https:\/\/mahmood.razzi.my\/feeds\/3837887429554068999\/comments\/default","title":"Post Comments"},{"rel":"replies","type":"text/html","href":"https:\/\/www.blogger.com\/comment\/fullpage\/post\/3214439820919958302\/3837887429554068999","title":"0 Comments"},{"rel":"edit","type":"application/atom+xml","href":"https:\/\/www.blogger.com\/feeds\/3214439820919958302\/posts\/default\/3837887429554068999"},{"rel":"self","type":"application/atom+xml","href":"https:\/\/www.blogger.com\/feeds\/3214439820919958302\/posts\/default\/3837887429554068999"},{"rel":"alternate","type":"text/html","href":"https:\/\/mahmood.razzi.my\/2022\/06\/crowd-decision-making-sparse.html","title":"Crowd Decision Making: Sparse Representation Guided by Sentiment Analysis for Leveraging the Wisdom of the Crowd"}],"author":[{"name":{"$t":"Unknown"},"email":{"$t":"noreply@blogger.com"},"gd$image":{"rel":"http://schemas.google.com/g/2005#thumbnail","width":"16","height":"16","src":"https:\/\/img1.blogblog.com\/img\/b16-rounded.gif"}}],"thr$total":{"$t":"0"}},{"id":{"$t":"tag:blogger.com,1999:blog-3214439820919958302.post-5500201706898546999"},"published":{"$t":"2022-06-17T15:08:00.008+08:00"},"updated":{"$t":"2023-01-26T15:10:54.976+08:00"},"category":[{"scheme":"http://www.blogger.com/atom/ns#","term":"*jour*"},{"scheme":"http://www.blogger.com/atom/ns#","term":"convolutional"},{"scheme":"http://www.blogger.com/atom/ns#","term":"deep-learning"},{"scheme":"http://www.blogger.com/atom/ns#","term":"embedding"},{"scheme":"http://www.blogger.com/atom/ns#","term":"emotion-analysis"},{"scheme":"http://www.blogger.com/atom/ns#","term":"long-short-term-memory"},{"scheme":"http://www.blogger.com/atom/ns#","term":"text-analysis"}],"title":{"type":"text","$t":"Deep Learning-Based Text Emotion Analysis for Legal Anomie"},"content":{"type":"html","$t":"\u003Cp\u003E***\u003C\/p\u003E\u003Cp\u003EAbstract:\u003C\/p\u003E\u003Cp\u003EText emotion analysis is an effective way for analyzing the emotion of the subjects’ anomie behaviors.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EThis paper proposes a text emotion analysis framework (called BCDF) based on word embedding and splicing.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EBi-direction Convolutional Word Embedding Classification Framework (BCDF) can express the word vector in the text and embed the part of speech tagging information as a feature of sentence representation.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EIn addition, an emotional parallel learning mechanism is proposed, which uses the temporal information of the parallel structure calculated by Bi-LSTM to update the storage information through the gating mechanism.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EThe convolutional layer can better extract certain components of sentences (such as adjectives, adverbs, nouns, etc.), which play a more significant role in the expression of emotion.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003ETo take advantage of convolution, a Convolutional Long Short-Term Memory (ConvLSTM) network is designed to further improve the classification results.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EExperimental results show that compared with traditional LSTM model, the proposed text emotion analysis model has increased 3.3 and 10.9% F1 score on psychological and news text datasets, respectively.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EThe proposed CBDM model based on Bi-LSTM and ConvLSTM has great value in practical applications of anomie behavior analysis.\u003C\/p\u003E\u003Cp\u003E***\u0026nbsp;\u003C\/p\u003E"},"link":[{"rel":"replies","type":"application/atom+xml","href":"https:\/\/mahmood.razzi.my\/feeds\/5500201706898546999\/comments\/default","title":"Post Comments"},{"rel":"replies","type":"text/html","href":"https:\/\/www.blogger.com\/comment\/fullpage\/post\/3214439820919958302\/5500201706898546999","title":"0 Comments"},{"rel":"edit","type":"application/atom+xml","href":"https:\/\/www.blogger.com\/feeds\/3214439820919958302\/posts\/default\/5500201706898546999"},{"rel":"self","type":"application/atom+xml","href":"https:\/\/www.blogger.com\/feeds\/3214439820919958302\/posts\/default\/5500201706898546999"},{"rel":"alternate","type":"text/html","href":"https:\/\/mahmood.razzi.my\/2022\/06\/deep-learning-based-text-emotion_17.html","title":"Deep Learning-Based Text Emotion Analysis for Legal Anomie"}],"author":[{"name":{"$t":"Unknown"},"email":{"$t":"noreply@blogger.com"},"gd$image":{"rel":"http://schemas.google.com/g/2005#thumbnail","width":"16","height":"16","src":"https:\/\/img1.blogblog.com\/img\/b16-rounded.gif"}}],"thr$total":{"$t":"0"}},{"id":{"$t":"tag:blogger.com,1999:blog-3214439820919958302.post-726292458674466930"},"published":{"$t":"2022-06-09T02:07:00.004+08:00"},"updated":{"$t":"2023-01-22T13:04:08.916+08:00"},"category":[{"scheme":"http://www.blogger.com/atom/ns#","term":"*jour*"},{"scheme":"http://www.blogger.com/atom/ns#","term":"nlp-model"},{"scheme":"http://www.blogger.com/atom/ns#","term":"text-analysis"},{"scheme":"http://www.blogger.com/atom/ns#","term":"text-classification"},{"scheme":"http://www.blogger.com/atom/ns#","term":"text-mining"},{"scheme":"http://www.blogger.com/atom/ns#","term":"textual-emotion-analysis"}],"title":{"type":"text","$t":"A Complete Process of Text Classification System Using State-of-the-Art NLP Models"},"content":{"type":"html","$t":"\u003Cp\u003E***\u003C\/p\u003E\u003Cp\u003EAbstract:\u003C\/p\u003E\u003Cp\u003EWith the rapid advancement of information technology, online information has been exponentially growing day by day, especially in the form of text documents such as news events, company reports, reviews on products, stocks-related reports, medical reports, tweets, and so on.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EDue to this, online monitoring and text mining has become a prominent task.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EDuring the past decade, significant efforts have been made on mining text documents using machine and deep learning models such as supervised, semisupervised, and unsupervised.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EOur area of the discussion covers state-of-the-art learning models for text mining or solving various challenging NLP (natural language processing) problems using the classification of texts.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EThis paper summarizes several machine learning and deep learning algorithms used in text classification with their advantages and shortcomings.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EThis paper would also help the readers understand various subtasks, along with old and recent literature, required during the process of text classification.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EWe believe that readers would be able to find scope for further improvements in the area of text classification or to propose new techniques of text classification applicable in any domain of their interest.\u003C\/p\u003E\u003Cp\u003E***\u0026nbsp;\u003C\/p\u003E\u003Cp\u003E\u003Ca href=\"https:\/\/www.hindawi.com\/journals\/cin\/2022\/1883698\/\"\u003Ehttps:\/\/www.hindawi.com\/journals\/cin\/2022\/1883698\/\u003C\/a\u003E\u003C\/p\u003E\u003Cp\u003E***\u003C\/p\u003E"},"link":[{"rel":"replies","type":"application/atom+xml","href":"https:\/\/mahmood.razzi.my\/feeds\/726292458674466930\/comments\/default","title":"Post Comments"},{"rel":"replies","type":"text/html","href":"https:\/\/www.blogger.com\/comment\/fullpage\/post\/3214439820919958302\/726292458674466930","title":"0 Comments"},{"rel":"edit","type":"application/atom+xml","href":"https:\/\/www.blogger.com\/feeds\/3214439820919958302\/posts\/default\/726292458674466930"},{"rel":"self","type":"application/atom+xml","href":"https:\/\/www.blogger.com\/feeds\/3214439820919958302\/posts\/default\/726292458674466930"},{"rel":"alternate","type":"text/html","href":"https:\/\/mahmood.razzi.my\/2022\/06\/a-complete-process-of-text.html","title":"A Complete Process of Text Classification System Using State-of-the-Art NLP Models"}],"author":[{"name":{"$t":"Unknown"},"email":{"$t":"noreply@blogger.com"},"gd$image":{"rel":"http://schemas.google.com/g/2005#thumbnail","width":"16","height":"16","src":"https:\/\/img1.blogblog.com\/img\/b16-rounded.gif"}}],"thr$total":{"$t":"0"}},{"id":{"$t":"tag:blogger.com,1999:blog-3214439820919958302.post-8809284466866602613"},"published":{"$t":"2022-05-31T01:55:00.005+08:00"},"updated":{"$t":"2023-01-21T02:00:29.521+08:00"},"category":[{"scheme":"http://www.blogger.com/atom/ns#","term":"*jour*"},{"scheme":"http://www.blogger.com/atom/ns#","term":"emotion-analysis"},{"scheme":"http://www.blogger.com/atom/ns#","term":"emotion-lexicon"},{"scheme":"http://www.blogger.com/atom/ns#","term":"lexicon"}],"title":{"type":"text","$t":"A multi-label emoji classification method using balanced pointwise mutual information-based feature selection"},"content":{"type":"html","$t":"\u003Cp\u003E***\u003C\/p\u003E\u003Cp\u003EAbstract:\u003C\/p\u003E\u003Cp\u003EThe availability of social media such as twitter allows users to express their feeling, emotions and opinions toward a topic.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EEmojis are graphic symbols that are regarded as the new generation of emoticons and an effective way of conveying feelings and emotions in social media.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EWith the surging popularity of Emojis, the researchers in the area of Emotion Classification strive to understand the emotion correlated to each Emoji.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003ETwo of the most the successful approaches in emoji analysis rely on: 1) official Unicode description and 2) manually built emoji lexicons.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003ESince the use of emoji is socially determined, the former approach is not aligned with intended semantic and usage, which leads researchers to opt for emoji lexicons.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003ETo overcome problem of lexicon-based approach, we proposed a method to classify emojis automatically.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003ETherefore, we present a modified Pointwise Mutual Information (PMI) method, called Balanced Pointwise Mutual Information-Based (B-PMI), to develop a balanced weighted emoji classification based on the semantic similarity.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EFurther, deep neural network is used to represent emoji in vector form (emoji embedding) to extend the pre-trained word embeddings.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EWe carefully evaluated the proposed method in multiple twitter datasets that are employed in sentiment and emotion classification using machine learning (ML) and deep learning (DL) approaches.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EIn both approaches, extending word embedding with the proposed emoji embedding improved results.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EThe DL-based approach achieved the highest f1-score of 70.01% for sentiment classification, and accuracy score of 56.36% for emotion classification.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EML-based approach obtained accuracy score of 52.17% in emotion classification.\u003C\/p\u003E\u003Cp\u003E***\u0026nbsp;\u003C\/p\u003E\u003Cp\u003E\u003Ca href=\"https:\/\/www.sciencedirect.com\/science\/article\/abs\/pii\/S0885230821001236\"\u003Ehttps:\/\/www.sciencedirect.com\/science\/article\/abs\/pii\/S0885230821001236\u003C\/a\u003E\u003C\/p\u003E\u003Cp\u003E\u003Ca href=\"https:\/\/drive.google.com\/file\/d\/1aAZkrGHdi5f8HSmHlHIIN4jRh6_houDL\/view?usp=share_link\"\u003E1aAZkrGHdi5f8HSmHlHIIN4jRh6_houDL\u003C\/a\u003E\u003C\/p\u003E\u003Cp\u003E***\u003C\/p\u003E"},"link":[{"rel":"replies","type":"application/atom+xml","href":"https:\/\/mahmood.razzi.my\/feeds\/8809284466866602613\/comments\/default","title":"Post Comments"},{"rel":"replies","type":"text/html","href":"https:\/\/www.blogger.com\/comment\/fullpage\/post\/3214439820919958302\/8809284466866602613","title":"0 Comments"},{"rel":"edit","type":"application/atom+xml","href":"https:\/\/www.blogger.com\/feeds\/3214439820919958302\/posts\/default\/8809284466866602613"},{"rel":"self","type":"application/atom+xml","href":"https:\/\/www.blogger.com\/feeds\/3214439820919958302\/posts\/default\/8809284466866602613"},{"rel":"alternate","type":"text/html","href":"https:\/\/mahmood.razzi.my\/2022\/05\/a-multi-label-emoji-classification.html","title":"A multi-label emoji classification method using balanced pointwise mutual information-based feature selection"}],"author":[{"name":{"$t":"Unknown"},"email":{"$t":"noreply@blogger.com"},"gd$image":{"rel":"http://schemas.google.com/g/2005#thumbnail","width":"16","height":"16","src":"https:\/\/img1.blogblog.com\/img\/b16-rounded.gif"}}],"thr$total":{"$t":"0"}},{"id":{"$t":"tag:blogger.com,1999:blog-3214439820919958302.post-1574210486710494025"},"published":{"$t":"2022-05-05T22:09:00.012+08:00"},"updated":{"$t":"2023-02-09T22:18:48.040+08:00"},"category":[{"scheme":"http://www.blogger.com/atom/ns#","term":"*jour*"},{"scheme":"http://www.blogger.com/atom/ns#","term":"lexicon-embedding"},{"scheme":"http://www.blogger.com/atom/ns#","term":"long-short-term-memory"},{"scheme":"http://www.blogger.com/atom/ns#","term":"negation-word"},{"scheme":"http://www.blogger.com/atom/ns#","term":"polar-word"},{"scheme":"http://www.blogger.com/atom/ns#","term":"sentiment-analysis"},{"scheme":"http://www.blogger.com/atom/ns#","term":"text-analysis"}],"title":{"type":"text","$t":"Two-Level LSTM for Sentiment Analysis With Lexicon Embedding and Polar Flipping"},"content":{"type":"html","$t":"\u003Cp\u003E***\u003C\/p\u003E\u003Cp\u003EAbstract:\u003C\/p\u003E\u003Cp\u003ESentiment analysis is a key component in various text mining applications.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003ENumerous sentiment classification techniques, including conventional and deep-learning-based methods, have been proposed in the literature.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EIn most existing methods, a high-quality training set is assumed to be given.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003ENevertheless, constructing a high-quality training set that consists of highly accurate labels is challenging in real applications.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EThis difficulty stems from the fact that text samples usually contain complex sentiment representations, and their annotation is subjective.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EWe address this challenge in this study by leveraging a new labeling strategy and utilizing a two-level long short-term memory network to construct a sentiment classifier.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003ELexical cues are useful for sentiment analysis, and they have been utilized in conventional studies.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EFor example, polar and negation words play important roles in sentiment analysis.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EA new encoding strategy, that is, ρ-hot encoding, is proposed to alleviate the drawbacks of one-hot encoding and, thus, effectively incorporate useful lexical cues.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EMoreover, the sentimental polarity of a word may change in different sentences due to label noise or context.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EA flipping model is proposed to model the polar flipping of words in a sentence.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EWe compile three Chinese datasets on the basis of our label strategy and proposed methodology.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EExperiments demonstrate that the proposed method outperforms state-of-the-art algorithms on both benchmark English data and our compiled Chinese data.\u003C\/p\u003E\u003Cp\u003E***\u0026nbsp;\u003C\/p\u003E\u003Cp\u003E\u003Ca href=\"https:\/\/ieeexplore.ieee.org\/document\/9204800\"\u003Ehttps:\/\/ieeexplore.ieee.org\/document\/9204800\u003C\/a\u003E\u003C\/p\u003E\u003Cp\u003E\u003Ca href=\"https:\/\/drive.google.com\/file\/d\/1SVeW00Uo2bPYIU1c1_x4U281ZjhiLPRN\/view?usp=share_link\" target=\"_blank\"\u003E\u0026gt;\u003C\/a\u003E\u003C\/p\u003E\u003Cp\u003E***\u003C\/p\u003E"},"link":[{"rel":"replies","type":"application/atom+xml","href":"https:\/\/mahmood.razzi.my\/feeds\/1574210486710494025\/comments\/default","title":"Post Comments"},{"rel":"replies","type":"text/html","href":"https:\/\/www.blogger.com\/comment\/fullpage\/post\/3214439820919958302\/1574210486710494025","title":"0 Comments"},{"rel":"edit","type":"application/atom+xml","href":"https:\/\/www.blogger.com\/feeds\/3214439820919958302\/posts\/default\/1574210486710494025"},{"rel":"self","type":"application/atom+xml","href":"https:\/\/www.blogger.com\/feeds\/3214439820919958302\/posts\/default\/1574210486710494025"},{"rel":"alternate","type":"text/html","href":"https:\/\/mahmood.razzi.my\/2022\/05\/two-level-lstm-for-sentiment-analysis.html","title":"Two-Level LSTM for Sentiment Analysis With Lexicon Embedding and Polar Flipping"}],"author":[{"name":{"$t":"Unknown"},"email":{"$t":"noreply@blogger.com"},"gd$image":{"rel":"http://schemas.google.com/g/2005#thumbnail","width":"16","height":"16","src":"https:\/\/img1.blogblog.com\/img\/b16-rounded.gif"}}],"thr$total":{"$t":"0"}},{"id":{"$t":"tag:blogger.com,1999:blog-3214439820919958302.post-5150715503692644218"},"published":{"$t":"2022-04-14T02:34:00.004+08:00"},"updated":{"$t":"2023-01-21T02:36:09.436+08:00"},"category":[{"scheme":"http://www.blogger.com/atom/ns#","term":"*jour*"},{"scheme":"http://www.blogger.com/atom/ns#","term":"hybrid"},{"scheme":"http://www.blogger.com/atom/ns#","term":"lexicon"}],"title":{"type":"text","$t":"Climate Change Sentiment Analysis Using Lexicon, Machine Learning and Hybrid Approaches"},"content":{"type":"html","$t":"\u003Cp\u003E***\u003C\/p\u003E\u003Cp\u003EAbstract:\u003C\/p\u003E\u003Cp\u003EThe emissions of greenhouse gases, such as carbon dioxide, into the biosphere have the consequence of warming up the planet, hence the existence of climate change.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003ESentiment analysis has been a popular subject and there has been a plethora of research conducted in this area in recent decades, typically on social media platforms such as Twitter, due to the proliferation of data generated today during discussions on climate change.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EHowever, there is not much research on the performances of different sentiment analysis approaches using lexicon, machine learning and hybrid methods, particularly within this domain-specific sentiment.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EThis study aims to find the most effective sentiment analysis approach for climate change tweets and related domains by performing a comparative evaluation of various sentiment analysis approaches.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EIn this context, seven lexicon-based approaches were used, namely SentiWordNet, TextBlob, VADER, SentiStrength, Hu and Liu, MPQA, and WKWSCI.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EMeanwhile, three machine learning classifiers were used, namely Support Vector Machine, Naïve Bayes, and Logistic Regression, by using two feature extraction techniques, which were Bag-of-Words and TF–IDF.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003ENext, the hybridization between lexicon-based and machine learning-based approaches was performed.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EThe results indicate that the hybrid method outperformed the other two approaches, with hybrid TextBlob and Logistic Regression achieving an F1-score of 75.3%; thus, this has been chosen as the most effective approach.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EThis study also found that lemmatization improved the accuracy of machine learning and hybrid approaches by 1.6%.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EMeanwhile, the TF–IDF feature extraction technique was slightly better than BoW by increasing the accuracy of the Logistic Regression classifier by 0.6%.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EHowever, TF–IDF and BoW had an identical effect on SVM and NB.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EFuture works will include investigating the suitability of deep learning approaches toward this domain-specific sentiment on social media platforms.\u003C\/p\u003E\u003Cp\u003EKeywords: climate change; sentiment analysis; lexicon; machine learning; social media\u003C\/p\u003E\u003Cp\u003E***\u0026nbsp;\u003C\/p\u003E\u003Cp\u003E\u003Ca href=\"https:\/\/www.mdpi.com\/2071-1050\/14\/8\/4723\"\u003Ehttps:\/\/www.mdpi.com\/2071-1050\/14\/8\/4723\u003C\/a\u003E\u003C\/p\u003E\u003Cp\u003E***\u003C\/p\u003E"},"link":[{"rel":"replies","type":"application/atom+xml","href":"https:\/\/mahmood.razzi.my\/feeds\/5150715503692644218\/comments\/default","title":"Post Comments"},{"rel":"replies","type":"text/html","href":"https:\/\/www.blogger.com\/comment\/fullpage\/post\/3214439820919958302\/5150715503692644218","title":"0 Comments"},{"rel":"edit","type":"application/atom+xml","href":"https:\/\/www.blogger.com\/feeds\/3214439820919958302\/posts\/default\/5150715503692644218"},{"rel":"self","type":"application/atom+xml","href":"https:\/\/www.blogger.com\/feeds\/3214439820919958302\/posts\/default\/5150715503692644218"},{"rel":"alternate","type":"text/html","href":"https:\/\/mahmood.razzi.my\/2022\/04\/climate-change-sentiment-analysis-using.html","title":"Climate Change Sentiment Analysis Using Lexicon, Machine Learning and Hybrid Approaches"}],"author":[{"name":{"$t":"Unknown"},"email":{"$t":"noreply@blogger.com"},"gd$image":{"rel":"http://schemas.google.com/g/2005#thumbnail","width":"16","height":"16","src":"https:\/\/img1.blogblog.com\/img\/b16-rounded.gif"}}],"thr$total":{"$t":"0"}},{"id":{"$t":"tag:blogger.com,1999:blog-3214439820919958302.post-5355759957825904886"},"published":{"$t":"2022-03-21T15:23:00.013+08:00"},"updated":{"$t":"2023-01-22T12:54:21.826+08:00"},"category":[{"scheme":"http://www.blogger.com/atom/ns#","term":"*jour*"},{"scheme":"http://www.blogger.com/atom/ns#","term":"BERT"},{"scheme":"http://www.blogger.com/atom/ns#","term":"blog"},{"scheme":"http://www.blogger.com/atom/ns#","term":"convolutional"},{"scheme":"http://www.blogger.com/atom/ns#","term":"deep-learning"},{"scheme":"http://www.blogger.com/atom/ns#","term":"feature-extraction"},{"scheme":"http://www.blogger.com/atom/ns#","term":"hate-speech"},{"scheme":"http://www.blogger.com/atom/ns#","term":"lexicon"},{"scheme":"http://www.blogger.com/atom/ns#","term":"logistics"},{"scheme":"http://www.blogger.com/atom/ns#","term":"n-gram"},{"scheme":"http://www.blogger.com/atom/ns#","term":"social-networking"},{"scheme":"http://www.blogger.com/atom/ns#","term":"support-vector-machines"},{"scheme":"http://www.blogger.com/atom/ns#","term":"tf-idf"}],"title":{"type":"text","$t":"Political Hate Speech Detection and Lexicon Building: A Study in Taiwan"},"content":{"type":"html","$t":"\u003Cp\u003E***\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EAbstract:\u003C\/p\u003E\u003Cp\u003EThere is the minimal restriction to users’ speech in cyberspace.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EThe Internet provides a space where people can freely present their speech, which puts a Utopian sense of freedom of speech into practice.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EHowever, the appearance of hate speech is a significant side effect of online freedom of speech.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003ESome users use hate speech to attack others, making the attacked targets uncomfortable.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EThe proliferation of hate speech poses severe challenges to cyber society.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EUsers may hope that social media platforms and online communities promote anti-hate speech.\u003C\/p\u003E\u003Cp\u003EHowever, hate speech detection is still a developing technology that requires system developers to create a method to detect unacceptable hate speech while maintaining the online freedom of speech environment.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003ENo excellence detection approach has yet been proposed, although some literature has focused on it.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EThe current study proposes an approach to build a political hate speech lexicon and train artificial intelligence classifiers to detect hate speech.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EOur academic and practical contributions include the collection of a Chinese hate speech dataset, creating a Chinese hate speech lexicon, and developing both a deep learning-based and a lexicon-based approach to detect Chinese hate speech.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EAlthough we focus on Chinese hate speech detection, our proposed hate speech detection system and hate speech lexicon development approach can also be used for other languages.\u003C\/p\u003E\u003Cp\u003E***\u003C\/p\u003E\u003Cp\u003E[i--\u003Ca href=\"https:\/\/doi.org\/10.1109\/ACCESS.2022.3160712\" target=\"_blank\"\u003Ehttps:\/\/doi.org\/10.1109\/ACCESS.2022.3160712\u003C\/a\u003E]\u003C\/p\u003E\u003Cp\u003E[p--\u003Ca href=\"https:\/\/ieeexplore.ieee.org\/document\/9738642\" target=\"_blank\"\u003Ehttps:\/\/ieeexplore.ieee.org\/document\/9738642\u003C\/a\u003E]\u003C\/p\u003E\u003Cp\u003E[d--\u003Ca href=\"https:\/\/ieeexplore.ieee.org\/stamp\/stamp.jsp?arnumber=9738642\"\u003Ehttps:\/\/ieeexplore.ieee.org\/stamp\/stamp.jsp?arnumber=9738642\u003C\/a\u003E]\u003C\/p\u003E\u003Cp\u003E[s--\u003Ca href=\"https:\/\/www.semanticscholar.org\/paper\/Political-Hate-Speech-Detection-and-Lexicon-A-Study-Wang-Day\/4e9dbc6ef31aee734680acedf5456032895d7fbf\"\u003Ehttps:\/\/www.semanticscholar.org\/paper\/Political-Hate-Speech-Detection-and-Lexicon-A-Study-Wang-Day\/4e9dbc6ef31aee734680acedf5456032895d7fbf\u003C\/a\u003E]\u003C\/p\u003E\u003Cp\u003E***\u003C\/p\u003E\u003Cp\u003E\u003Cbr \/\u003E\u003C\/p\u003E"},"link":[{"rel":"replies","type":"application/atom+xml","href":"https:\/\/mahmood.razzi.my\/feeds\/5355759957825904886\/comments\/default","title":"Post Comments"},{"rel":"replies","type":"text/html","href":"https:\/\/www.blogger.com\/comment\/fullpage\/post\/3214439820919958302\/5355759957825904886","title":"0 Comments"},{"rel":"edit","type":"application/atom+xml","href":"https:\/\/www.blogger.com\/feeds\/3214439820919958302\/posts\/default\/5355759957825904886"},{"rel":"self","type":"application/atom+xml","href":"https:\/\/www.blogger.com\/feeds\/3214439820919958302\/posts\/default\/5355759957825904886"},{"rel":"alternate","type":"text/html","href":"https:\/\/mahmood.razzi.my\/2022\/03\/political-hate-speech-detection-and.html","title":"Political Hate Speech Detection and Lexicon Building: A Study in Taiwan"}],"author":[{"name":{"$t":"Unknown"},"email":{"$t":"noreply@blogger.com"},"gd$image":{"rel":"http://schemas.google.com/g/2005#thumbnail","width":"16","height":"16","src":"https:\/\/img1.blogblog.com\/img\/b16-rounded.gif"}}],"thr$total":{"$t":"0"}},{"id":{"$t":"tag:blogger.com,1999:blog-3214439820919958302.post-4668193841406363855"},"published":{"$t":"2022-01-26T02:28:00.009+08:00"},"updated":{"$t":"2023-01-22T12:56:23.294+08:00"},"category":[{"scheme":"http://www.blogger.com/atom/ns#","term":"*jour*"},{"scheme":"http://www.blogger.com/atom/ns#","term":"BERT"},{"scheme":"http://www.blogger.com/atom/ns#","term":"lexicon"},{"scheme":"http://www.blogger.com/atom/ns#","term":"neural"},{"scheme":"http://www.blogger.com/atom/ns#","term":"sentiment-analysis"}],"title":{"type":"text","$t":"Lexicon-Based vs. Bert-Based Sentiment Analysis: A Comparative Study in Italian"},"content":{"type":"html","$t":"\u003Cp\u003E***\u003C\/p\u003E\u003Cp\u003EAbstract:\u003C\/p\u003E\u003Cp\u003ERecent evolutions in the e-commerce market have led to an increasing importance attributed by consumers to product reviews made by third parties before proceeding to purchase.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EThe industry, in order to improve the offer intercepting the discontent of consumers, has placed increasing attention towards systems able to identify the sentiment expressed by buyers, whether positive or negative.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EFrom a technological point of view, the literature in recent years has seen the development of two types of methodologies: those based on lexicons and those based on machine and deep learning techniques.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EThis study proposes a comparison between these technologies in the Italian market, one of the largest in the world, exploiting an ad hoc dataset: scientific evidence generally shows the superiority of language models such as BERT built on deep neural networks, but it opens several considerations on the effectiveness and improvement of these solutions when compared to those based on lexicons in the presence of datasets of reduced size such as the one under study, a common condition for languages other than English or Chinese.\u003C\/p\u003E\u003Cp\u003EKeywords: sentiment analysis; review; Italian; lexicon; nooj; deep learning; BERT\u003C\/p\u003E\u003Cp\u003E***\u003C\/p\u003E\u003Cp\u003E\u003Ca href=\"https:\/\/www.mdpi.com\/2079-9292\/11\/3\/374\"\u003Ehttps:\/\/www.mdpi.com\/2079-9292\/11\/3\/374\u003C\/a\u003E\u003C\/p\u003E\u003Cp\u003E\u003Cbr \/\u003E\u003C\/p\u003E\u003Cp\u003E***\u0026nbsp;\u003C\/p\u003E"},"link":[{"rel":"replies","type":"application/atom+xml","href":"https:\/\/mahmood.razzi.my\/feeds\/4668193841406363855\/comments\/default","title":"Post Comments"},{"rel":"replies","type":"text/html","href":"https:\/\/www.blogger.com\/comment\/fullpage\/post\/3214439820919958302\/4668193841406363855","title":"0 Comments"},{"rel":"edit","type":"application/atom+xml","href":"https:\/\/www.blogger.com\/feeds\/3214439820919958302\/posts\/default\/4668193841406363855"},{"rel":"self","type":"application/atom+xml","href":"https:\/\/www.blogger.com\/feeds\/3214439820919958302\/posts\/default\/4668193841406363855"},{"rel":"alternate","type":"text/html","href":"https:\/\/mahmood.razzi.my\/2022\/01\/lexicon-based-vs-bert-based-sentiment.html","title":"Lexicon-Based vs. Bert-Based Sentiment Analysis: A Comparative Study in Italian"}],"author":[{"name":{"$t":"Unknown"},"email":{"$t":"noreply@blogger.com"},"gd$image":{"rel":"http://schemas.google.com/g/2005#thumbnail","width":"16","height":"16","src":"https:\/\/img1.blogblog.com\/img\/b16-rounded.gif"}}],"thr$total":{"$t":"0"}},{"id":{"$t":"tag:blogger.com,1999:blog-3214439820919958302.post-8446112092404528200"},"published":{"$t":"2022-01-12T23:03:00.004+08:00"},"updated":{"$t":"2023-01-22T23:05:17.384+08:00"},"category":[{"scheme":"http://www.blogger.com/atom/ns#","term":"*jour*"},{"scheme":"http://www.blogger.com/atom/ns#","term":"deep-learning"},{"scheme":"http://www.blogger.com/atom/ns#","term":"emotion-detection"},{"scheme":"http://www.blogger.com/atom/ns#","term":"text-analysis"},{"scheme":"http://www.blogger.com/atom/ns#","term":"textual-emotion-analysis"}],"title":{"type":"text","$t":"Deep learning approach to text analysis for human emotion detection from big data"},"content":{"type":"html","$t":"\u003Cp\u003E***\u003C\/p\u003E\u003Cp\u003EAbstract:\u003C\/p\u003E\u003Cp\u003EEmotional recognition has arisen as an essential field of study that can expose a variety of valuable inputs.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EEmotion can be articulated in several means that can be seen, like speech and facial expressions, written text, and gestures.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EEmotion recognition in a text document is fundamentally a content-based classification issue, including notions from natural language processing (NLP) and deep learning fields.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EHence, in this study, deep learning assisted semantic text analysis (DLSTA) has been proposed for human emotion detection using big data.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EEmotion detection from textual sources can be done utilizing notions of Natural Language Processing.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EWord embeddings are extensively utilized for several NLP tasks, like machine translation, sentiment analysis, and question answering.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003ENLP techniques improve the performance of learning-based methods by incorporating the semantic and syntactic features of the text.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EThe numerical outcomes demonstrate that the suggested method achieves an expressively superior quality of human emotion detection rate of 97.22% and the classification accuracy rate of 98.02% with different state-of-the-art methods and can be enhanced by other emotional word embeddings.\u003C\/p\u003E\u003Cp\u003E***\u003C\/p\u003E\u003Cp\u003EKeywords: deep learning; text analysis; human emotion detection; NLP\u003C\/p\u003E\u003Cp\u003E***\u0026nbsp;\u003C\/p\u003E\u003Cp\u003E\u003Ca href=\"https:\/\/www.degruyter.com\/document\/doi\/10.1515\/jisys-2022-0001\/html?lang=en\"\u003Ehttps:\/\/www.degruyter.com\/document\/doi\/10.1515\/jisys-2022-0001\/html?lang=en\u003C\/a\u003E\u003C\/p\u003E\u003Cp\u003E\u003Ca href=\"https:\/\/www.degruyter.com\/document\/doi\/10.1515\/jisys-2022-0001\/pdf\"\u003Ehttps:\/\/www.degruyter.com\/document\/doi\/10.1515\/jisys-2022-0001\/pdf\u003C\/a\u003E\u003C\/p\u003E\u003Cp\u003E***\u003C\/p\u003E"},"link":[{"rel":"replies","type":"application/atom+xml","href":"https:\/\/mahmood.razzi.my\/feeds\/8446112092404528200\/comments\/default","title":"Post Comments"},{"rel":"replies","type":"text/html","href":"https:\/\/www.blogger.com\/comment\/fullpage\/post\/3214439820919958302\/8446112092404528200","title":"0 Comments"},{"rel":"edit","type":"application/atom+xml","href":"https:\/\/www.blogger.com\/feeds\/3214439820919958302\/posts\/default\/8446112092404528200"},{"rel":"self","type":"application/atom+xml","href":"https:\/\/www.blogger.com\/feeds\/3214439820919958302\/posts\/default\/8446112092404528200"},{"rel":"alternate","type":"text/html","href":"https:\/\/mahmood.razzi.my\/2022\/01\/deep-learning-approach-to-text-analysis_12.html","title":"Deep learning approach to text analysis for human emotion detection from big data"}],"author":[{"name":{"$t":"Unknown"},"email":{"$t":"noreply@blogger.com"},"gd$image":{"rel":"http://schemas.google.com/g/2005#thumbnail","width":"16","height":"16","src":"https:\/\/img1.blogblog.com\/img\/b16-rounded.gif"}}],"thr$total":{"$t":"0"}},{"id":{"$t":"tag:blogger.com,1999:blog-3214439820919958302.post-5636399469674613058"},"published":{"$t":"2022-01-12T13:06:00.010+08:00"},"updated":{"$t":"2023-01-22T13:09:18.206+08:00"},"category":[{"scheme":"http://www.blogger.com/atom/ns#","term":"*jour*"},{"scheme":"http://www.blogger.com/atom/ns#","term":"deep-learning"},{"scheme":"http://www.blogger.com/atom/ns#","term":"neural"},{"scheme":"http://www.blogger.com/atom/ns#","term":"text-analysis"},{"scheme":"http://www.blogger.com/atom/ns#","term":"textual-emotion-analysis"}],"title":{"type":"text","$t":"Deep learning approach to text analysis for human emotion detection from big data"},"content":{"type":"html","$t":"\u003Cp\u003E***\u003C\/p\u003E\u003Cp\u003EAbstract:\u003C\/p\u003E\u003Cp\u003EEmotional recognition has arisen as an essential field of study that can expose a variety of valuable inputs.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EEmotion can be articulated in several means that can be seen, like speech and facial expressions, written text, and gestures.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EEmotion recognition in a text document is fundamentally a content-based classification issue, including notions from natural language processing (NLP) and deep learning fields.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EHence, in this study, deep learning assisted semantic text analysis (DLSTA) has been proposed for human emotion detection using big data.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EEmotion detection from textual sources can be done utilizing notions of Natural Language Processing.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EWord embeddings are extensively utilized for several NLP tasks, like machine translation, sentiment analysis, and question answering.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003ENLP techniques improve the performance of learning-based methods by incorporating the semantic and syntactic features of the text.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EThe numerical outcomes demonstrate that the suggested method achieves an expressively superior quality of human emotion detection rate of 97.22% and the classification accuracy rate of 98.02% with different state-of-the-art methods and can be enhanced by other emotional word embeddings.\u003C\/p\u003E\u003Cp\u003E***\u003C\/p\u003E\u003Cp\u003EKeywords: deep learning; text analysis; human emotion detection; NLP\u0026nbsp;\u003C\/p\u003E\u003Cp\u003E***\u003C\/p\u003E\u003Cp\u003Ehttps:\/\/www.degruyter.com\/document\/doi\/10.1515\/jisys-2022-0001\/html\u003C\/p\u003E\u003Cp\u003E***\u003C\/p\u003E"},"link":[{"rel":"replies","type":"application/atom+xml","href":"https:\/\/mahmood.razzi.my\/feeds\/5636399469674613058\/comments\/default","title":"Post Comments"},{"rel":"replies","type":"text/html","href":"https:\/\/www.blogger.com\/comment\/fullpage\/post\/3214439820919958302\/5636399469674613058","title":"0 Comments"},{"rel":"edit","type":"application/atom+xml","href":"https:\/\/www.blogger.com\/feeds\/3214439820919958302\/posts\/default\/5636399469674613058"},{"rel":"self","type":"application/atom+xml","href":"https:\/\/www.blogger.com\/feeds\/3214439820919958302\/posts\/default\/5636399469674613058"},{"rel":"alternate","type":"text/html","href":"https:\/\/mahmood.razzi.my\/2022\/01\/deep-learning-approach-to-text-analysis.html","title":"Deep learning approach to text analysis for human emotion detection from big data"}],"author":[{"name":{"$t":"Unknown"},"email":{"$t":"noreply@blogger.com"},"gd$image":{"rel":"http://schemas.google.com/g/2005#thumbnail","width":"16","height":"16","src":"https:\/\/img1.blogblog.com\/img\/b16-rounded.gif"}}],"thr$total":{"$t":"0"}},{"id":{"$t":"tag:blogger.com,1999:blog-3214439820919958302.post-7220865742090717263"},"published":{"$t":"2022-01-12T01:02:00.005+08:00"},"updated":{"$t":"2023-01-23T01:04:18.332+08:00"},"category":[{"scheme":"http://www.blogger.com/atom/ns#","term":"*jour*"},{"scheme":"http://www.blogger.com/atom/ns#","term":"clustering"},{"scheme":"http://www.blogger.com/atom/ns#","term":"deep-learning"},{"scheme":"http://www.blogger.com/atom/ns#","term":"emotion-detection"},{"scheme":"http://www.blogger.com/atom/ns#","term":"text-analysis"},{"scheme":"http://www.blogger.com/atom/ns#","term":"textual-emotion-analysis"}],"title":{"type":"text","$t":"Deep learning approach to text analysis for human emotion detection from big data"},"content":{"type":"html","$t":"\u003Cp\u003E***\u003C\/p\u003E\u003Cp\u003EAbstract:\u003C\/p\u003E\u003Cp\u003EEmotional recognition has arisen as an essential field of study that can expose a variety of valuable inputs.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EEmotion can be articulated in several means that can be seen, like speech and facial expressions, written text, and gestures.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EEmotion recognition in a text document is fundamentally a content-based classification issue, including notions from natural language processing (NLP) and deep learning fields.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EHence, in this study, deep learning assisted semantic text analysis (DLSTA) has been proposed for human emotion detection using big data.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EEmotion detection from textual sources can be done utilizing notions of Natural Language Processing.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EWord embeddings are extensively utilized for several NLP tasks, like machine translation, sentiment analysis, and question answering.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003ENLP techniques improve the performance of learning-based methods by incorporating the semantic and syntactic features of the text.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EThe numerical outcomes demonstrate that the suggested method achieves an expressively superior quality of human emotion detection rate of 97.22% and the classification accuracy rate of 98.02% with different state-of-the-art methods and can be enhanced by other emotional word embeddings.\u003C\/p\u003E\u003Cp\u003E***\u0026nbsp;\u003C\/p\u003E\u003Cp\u003E\u003Ca href=\"https:\/\/www.degruyter.com\/document\/doi\/10.1515\/jisys-2022-0001\/html\"\u003Ehttps:\/\/www.degruyter.com\/document\/doi\/10.1515\/jisys-2022-0001\/html\u003C\/a\u003E\u003C\/p\u003E\u003Cp\u003E\u003Cbr \/\u003E\u003C\/p\u003E\u003Cp\u003E***\u003C\/p\u003E"},"link":[{"rel":"replies","type":"application/atom+xml","href":"https:\/\/mahmood.razzi.my\/feeds\/7220865742090717263\/comments\/default","title":"Post Comments"},{"rel":"replies","type":"text/html","href":"https:\/\/www.blogger.com\/comment\/fullpage\/post\/3214439820919958302\/7220865742090717263","title":"0 Comments"},{"rel":"edit","type":"application/atom+xml","href":"https:\/\/www.blogger.com\/feeds\/3214439820919958302\/posts\/default\/7220865742090717263"},{"rel":"self","type":"application/atom+xml","href":"https:\/\/www.blogger.com\/feeds\/3214439820919958302\/posts\/default\/7220865742090717263"},{"rel":"alternate","type":"text/html","href":"https:\/\/mahmood.razzi.my\/2022\/01\/deep-learning-approach-to-text-analysis_59.html","title":"Deep learning approach to text analysis for human emotion detection from big data"}],"author":[{"name":{"$t":"Unknown"},"email":{"$t":"noreply@blogger.com"},"gd$image":{"rel":"http://schemas.google.com/g/2005#thumbnail","width":"16","height":"16","src":"https:\/\/img1.blogblog.com\/img\/b16-rounded.gif"}}],"thr$total":{"$t":"0"}},{"id":{"$t":"tag:blogger.com,1999:blog-3214439820919958302.post-1220971667271958712"},"published":{"$t":"2021-10-11T23:42:00.005+08:00"},"updated":{"$t":"2023-02-09T23:46:43.404+08:00"},"category":[{"scheme":"http://www.blogger.com/atom/ns#","term":"*jour*"},{"scheme":"http://www.blogger.com/atom/ns#","term":"deep-learning"}],"title":{"type":"text","$t":"Learning Causal Representations for Robust Domain Adaptation"},"content":{"type":"html","$t":"\u003Cp\u003E***\u003C\/p\u003E\u003Cp\u003EAbstract:\u003C\/p\u003E\u003Cp\u003EIn this study, we investigate a challenging problem, namely, robust domain adaptation, where data from only a single well-labeled source domain are available in the training phase.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003ETo address this problem, assuming that the causal relationships between the features and the class variable are robust across domains, we propose a novel causal autoencoder (CAE), which integrates a deep autoencoder and a causal structure learning model to learn causal representations using data from a single source domain.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003ESpecifically, a deep autoencoder model is adopted to learn the low-dimensional representations, and a causal structure learning model is designed to separate the low-dimensional representations into two groups: causal representations and task-irrelevant representations.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EUsing three real-world datasets, the experiments have validated the effectiveness of CAE, in comparison with eleven state-of-the-art methods.\u003C\/p\u003E\u003Cp\u003E***\u0026nbsp;\u003C\/p\u003E\u003Cp\u003E\u003Ca href=\"https:\/\/ieeexplore.ieee.org\/document\/9566788\"\u003Ehttps:\/\/ieeexplore.ieee.org\/document\/9566788\u003C\/a\u003E\u003C\/p\u003E\u003Cp\u003E\u003Ca href=\"https:\/\/arxiv.org\/pdf\/2011.06317.pdf\"\u003Ehttps:\/\/arxiv.org\/pdf\/2011.06317.pdf\u003C\/a\u003E\u003C\/p\u003E\u003Cp\u003E***\u003C\/p\u003E"},"link":[{"rel":"replies","type":"application/atom+xml","href":"https:\/\/mahmood.razzi.my\/feeds\/1220971667271958712\/comments\/default","title":"Post Comments"},{"rel":"replies","type":"text/html","href":"https:\/\/www.blogger.com\/comment\/fullpage\/post\/3214439820919958302\/1220971667271958712","title":"0 Comments"},{"rel":"edit","type":"application/atom+xml","href":"https:\/\/www.blogger.com\/feeds\/3214439820919958302\/posts\/default\/1220971667271958712"},{"rel":"self","type":"application/atom+xml","href":"https:\/\/www.blogger.com\/feeds\/3214439820919958302\/posts\/default\/1220971667271958712"},{"rel":"alternate","type":"text/html","href":"https:\/\/mahmood.razzi.my\/2021\/10\/learning-causal-representations-for.html","title":"Learning Causal Representations for Robust Domain Adaptation"}],"author":[{"name":{"$t":"Unknown"},"email":{"$t":"noreply@blogger.com"},"gd$image":{"rel":"http://schemas.google.com/g/2005#thumbnail","width":"16","height":"16","src":"https:\/\/img1.blogblog.com\/img\/b16-rounded.gif"}}],"thr$total":{"$t":"0"}},{"id":{"$t":"tag:blogger.com,1999:blog-3214439820919958302.post-7090826551276235003"},"published":{"$t":"2021-04-06T22:04:00.011+08:00"},"updated":{"$t":"2023-02-09T22:08:37.120+08:00"},"category":[{"scheme":"http://www.blogger.com/atom/ns#","term":"*jour*"},{"scheme":"http://www.blogger.com/atom/ns#","term":"sentiment-analysis"},{"scheme":"http://www.blogger.com/atom/ns#","term":"stemming"},{"scheme":"http://www.blogger.com/atom/ns#","term":"text-analysis"}],"title":{"type":"text","$t":"Deep Sentiment Analysis: A Case Study on Stemmed Turkish Twitter Data"},"content":{"type":"html","$t":"\u003Cp\u003E***\u003C\/p\u003E\u003Cp\u003EAbstract:\u003C\/p\u003E\u003Cp\u003ESentiment analysis using stemmed Twitter data from various languages is an emerging research topic.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EIn this paper, we address three data augmentation techniques namely Shift, Shuffle, and Hybrid to increase the size of the training data; and then we use three key types of deep learning (DL) models namely recurrent neural network (RNN), convolution neural network (CNN), and hierarchical attention network (HAN) to classify the stemmed Turkish Twitter data for sentiment analysis.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EThe performance of these DL models has been compared with the existing traditional machine learning (TML) models.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EThe performance of TML models has been affected negatively by the stemmed data, but the performance of DL models has been improved greatly with the utilization of the augmentation techniques.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EBased on the simulation, experimental, and statistical results analysis deeming identical datasets, it has been concluded that the TML models outperform the DL models with respect to both training-time (TTM) and runtime (RTM) complexities of the algorithms; but the DL models outperform the TML models with respect to the most important performance factors as well as the average performance rankings.\u003C\/p\u003E\u003Cp\u003E***\u0026nbsp;\u003C\/p\u003E\u003Cp\u003E\u003Ca href=\"https:\/\/ieeexplore.ieee.org\/document\/9395633\"\u003Ehttps:\/\/ieeexplore.ieee.org\/document\/9395633\u003C\/a\u003E\u003C\/p\u003E\u003Cp\u003E\u003Ca href=\"https:\/\/ieeexplore.ieee.org\/stamp\/stamp.jsp?arnumber=9395633\"\u003Ehttps:\/\/ieeexplore.ieee.org\/stamp\/stamp.jsp?arnumber=9395633\u003C\/a\u003E\u003C\/p\u003E\u003Cp\u003E***\u003C\/p\u003E"},"link":[{"rel":"replies","type":"application/atom+xml","href":"https:\/\/mahmood.razzi.my\/feeds\/7090826551276235003\/comments\/default","title":"Post Comments"},{"rel":"replies","type":"text/html","href":"https:\/\/www.blogger.com\/comment\/fullpage\/post\/3214439820919958302\/7090826551276235003","title":"0 Comments"},{"rel":"edit","type":"application/atom+xml","href":"https:\/\/www.blogger.com\/feeds\/3214439820919958302\/posts\/default\/7090826551276235003"},{"rel":"self","type":"application/atom+xml","href":"https:\/\/www.blogger.com\/feeds\/3214439820919958302\/posts\/default\/7090826551276235003"},{"rel":"alternate","type":"text/html","href":"https:\/\/mahmood.razzi.my\/2021\/04\/deep-sentiment-analysis-case-study-on.html","title":"Deep Sentiment Analysis: A Case Study on Stemmed Turkish Twitter Data"}],"author":[{"name":{"$t":"Unknown"},"email":{"$t":"noreply@blogger.com"},"gd$image":{"rel":"http://schemas.google.com/g/2005#thumbnail","width":"16","height":"16","src":"https:\/\/img1.blogblog.com\/img\/b16-rounded.gif"}}],"thr$total":{"$t":"0"}},{"id":{"$t":"tag:blogger.com,1999:blog-3214439820919958302.post-5108588313242515190"},"published":{"$t":"2021-03-03T02:38:00.004+08:00"},"updated":{"$t":"2023-01-25T02:40:25.706+08:00"},"category":[{"scheme":"http://www.blogger.com/atom/ns#","term":"*jour*"},{"scheme":"http://www.blogger.com/atom/ns#","term":"sentiment-analysis"},{"scheme":"http://www.blogger.com/atom/ns#","term":"survey"}],"title":{"type":"text","$t":"Systematic reviews in sentiment analysis: a tertiary study"},"content":{"type":"html","$t":"\u003Cp\u003E***\u003C\/p\u003E\u003Cp\u003EAbstract:\u003C\/p\u003E\u003Cp\u003EWith advanced digitalisation, we can observe a massive increase of user-generated content on the web that provides opinions of people on different subjects.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003ESentiment analysis is the computational study of analysing people's feelings and opinions for an entity.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EThe field of sentiment analysis has been the topic of extensive research in the past decades.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EIn this paper, we present the results of a tertiary study, which aims to investigate the current state of the research in this field by synthesizing the results of published secondary studies (i.e., systematic literature review and systematic mapping study) on sentiment analysis.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EThis tertiary study follows the guidelines of systematic literature reviews (SLR) and covers only secondary studies.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EThe outcome of this tertiary study provides a comprehensive overview of the key topics and the different approaches for a variety of tasks in sentiment analysis.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EDifferent features, algorithms, and datasets used in sentiment analysis models are mapped.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EChallenges and open problems are identified that can help to identify points that require research efforts in sentiment analysis.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EIn addition to the tertiary study, we also identified recent 112 deep learning-based sentiment analysis papers and categorized them based on the applied deep learning algorithms.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EAccording to this analysis, LSTM and CNN algorithms are the most used deep learning algorithms for sentiment analysis.\u003C\/p\u003E\u003Cp\u003E***\u0026nbsp;\u003C\/p\u003E\u003Cp\u003E\u003Ca href=\"https:\/\/link.springer.com\/article\/10.1007\/s10462-021-09973-3\"\u003Ehttps:\/\/link.springer.com\/article\/10.1007\/s10462-021-09973-3\u003C\/a\u003E\u003C\/p\u003E\u003Cp\u003E\u003Cbr \/\u003E\u003C\/p\u003E\u003Cp\u003E***\u003C\/p\u003E"},"link":[{"rel":"replies","type":"application/atom+xml","href":"https:\/\/mahmood.razzi.my\/feeds\/5108588313242515190\/comments\/default","title":"Post Comments"},{"rel":"replies","type":"text/html","href":"https:\/\/www.blogger.com\/comment\/fullpage\/post\/3214439820919958302\/5108588313242515190","title":"0 Comments"},{"rel":"edit","type":"application/atom+xml","href":"https:\/\/www.blogger.com\/feeds\/3214439820919958302\/posts\/default\/5108588313242515190"},{"rel":"self","type":"application/atom+xml","href":"https:\/\/www.blogger.com\/feeds\/3214439820919958302\/posts\/default\/5108588313242515190"},{"rel":"alternate","type":"text/html","href":"https:\/\/mahmood.razzi.my\/2021\/03\/systematic-reviews-in-sentiment.html","title":"Systematic reviews in sentiment analysis: a tertiary study"}],"author":[{"name":{"$t":"Unknown"},"email":{"$t":"noreply@blogger.com"},"gd$image":{"rel":"http://schemas.google.com/g/2005#thumbnail","width":"16","height":"16","src":"https:\/\/img1.blogblog.com\/img\/b16-rounded.gif"}}],"thr$total":{"$t":"0"}},{"id":{"$t":"tag:blogger.com,1999:blog-3214439820919958302.post-1285448262573412309"},"published":{"$t":"2021-01-29T22:51:00.007+08:00"},"updated":{"$t":"2023-02-09T23:21:12.706+08:00"},"category":[{"scheme":"http://www.blogger.com/atom/ns#","term":"*jour*"},{"scheme":"http://www.blogger.com/atom/ns#","term":"deep-learning"},{"scheme":"http://www.blogger.com/atom/ns#","term":"sentiment-analysis"}],"title":{"type":"text","$t":"Spider Monkey Crow Optimization Algorithm With Deep Learning for Sentiment Classification and Information Retrieval"},"content":{"type":"html","$t":"\u003Cp\u003E***\u003C\/p\u003E\u003Cp\u003EAbstract:\u003C\/p\u003E\u003Cp\u003EThe epidemic increase in online reviews’ growth made the sentiment classification a fascinating domain in academic and industrial research.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EThe reviews assist several domains, which is complicated to gather annotated training data.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003ESeveral sentiment classification methodologies are devised for performing the sentiment analysis, but retrieval of information is not accurately performed, less effective, and less convergence speed.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EIn this paper, we propose a sentiment paper proposes a sentiment classification model, namely Spider Monkey Crow Optimization algorithm (SMCA), for training the deep recurrent neural network (DeepRNN).\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EIn this method, the telecom review is employed to remove stop words and stemming to eliminate inappropriate data to minimize user’s seeking time.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EMeanwhile, the feature extraction is performed using SentiWordNet to derive the sentiments from the reviews.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EThe extracted SentiWordNet features and other features, like elongated words, punctuation, hashtag, and numerical values, are employed in the DeepRNN for classifying sentiments.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003ETo retrieve the required review, the Fuzzy K-Nearest neighbor (Fuzzy-KNN) is employed to retrieve the review based on a distance measure.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EWith rigorous assessments and experimentation, it is observed that the proposed SMCA-based DeepRNN performs better in terms of accuracy of 97.7%, precision of 95.5%, recall of 94.6%, and F1-score 96.7%, respectively.\u003C\/p\u003E\u003Cp\u003E***\u0026nbsp;\u003C\/p\u003E\u003Cp\u003E\u003Ca href=\"https:\/\/ieeexplore.ieee.org\/document\/9340241\"\u003Ehttps:\/\/ieeexplore.ieee.org\/document\/9340241\u003C\/a\u003E\u003C\/p\u003E\u003Cp\u003E\u003Ca href=\"https:\/\/ieeexplore.ieee.org\/stamp\/stamp.jsp?arnumber=9340241\"\u003Ehttps:\/\/ieeexplore.ieee.org\/stamp\/stamp.jsp?arnumber=9340241\u003C\/a\u003E\u003C\/p\u003E\u003Cp\u003E***\u003C\/p\u003E"},"link":[{"rel":"replies","type":"application/atom+xml","href":"https:\/\/mahmood.razzi.my\/feeds\/1285448262573412309\/comments\/default","title":"Post Comments"},{"rel":"replies","type":"text/html","href":"https:\/\/www.blogger.com\/comment\/fullpage\/post\/3214439820919958302\/1285448262573412309","title":"0 Comments"},{"rel":"edit","type":"application/atom+xml","href":"https:\/\/www.blogger.com\/feeds\/3214439820919958302\/posts\/default\/1285448262573412309"},{"rel":"self","type":"application/atom+xml","href":"https:\/\/www.blogger.com\/feeds\/3214439820919958302\/posts\/default\/1285448262573412309"},{"rel":"alternate","type":"text/html","href":"https:\/\/mahmood.razzi.my\/2021\/01\/spider-monkey-crow-optimization.html","title":"Spider Monkey Crow Optimization Algorithm With Deep Learning for Sentiment Classification and Information Retrieval"}],"author":[{"name":{"$t":"Unknown"},"email":{"$t":"noreply@blogger.com"},"gd$image":{"rel":"http://schemas.google.com/g/2005#thumbnail","width":"16","height":"16","src":"https:\/\/img1.blogblog.com\/img\/b16-rounded.gif"}}],"thr$total":{"$t":"0"}},{"id":{"$t":"tag:blogger.com,1999:blog-3214439820919958302.post-3424546643616497528"},"published":{"$t":"2019-11-22T02:40:00.005+08:00"},"updated":{"$t":"2023-01-21T02:42:13.167+08:00"},"category":[{"scheme":"http://www.blogger.com/atom/ns#","term":"*jour*"},{"scheme":"http://www.blogger.com/atom/ns#","term":"sentiment-analysis"},{"scheme":"http://www.blogger.com/atom/ns#","term":"social-media"}],"title":{"type":"text","$t":"Sentiment Analysis for Social Media"},"content":{"type":"html","$t":"\u003Cp\u003E***\u003C\/p\u003E\u003Cp\u003EAbstract:\u003C\/p\u003E\u003Cp\u003ESentiment analysis has become a key technology to gain insight from social networks.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EThe field has reached a level of maturity that paves the way for its exploitation in many different fields such as marketing, health, banking or politics.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EThe latest technological advancements, such as deep learning techniques, have solved some of the traditional challenges in the area caused by the scarcity of lexical resources.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EIn this Special Issue, different approaches that advance this discipline are presented.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EThe contributed articles belong to two broad groups: technological contributions and applications.\u003C\/p\u003E\u003Cp\u003EKeywords: sentiment analysis; emotion analysis; social media; affect computing\u003C\/p\u003E\u003Cp\u003E\u003Cbr \/\u003E\u003C\/p\u003E\u003Cp\u003E***\u0026nbsp;\u003C\/p\u003E\u003Cp\u003E\u003Ca href=\"https:\/\/www.mdpi.com\/2076-3417\/9\/23\/5037\"\u003Ehttps:\/\/www.mdpi.com\/2076-3417\/9\/23\/5037\u003C\/a\u003E\u003C\/p\u003E\u003Cp\u003E\u003Cbr \/\u003E\u003C\/p\u003E\u003Cp\u003E***\u003C\/p\u003E"},"link":[{"rel":"replies","type":"application/atom+xml","href":"https:\/\/mahmood.razzi.my\/feeds\/3424546643616497528\/comments\/default","title":"Post Comments"},{"rel":"replies","type":"text/html","href":"https:\/\/www.blogger.com\/comment\/fullpage\/post\/3214439820919958302\/3424546643616497528","title":"0 Comments"},{"rel":"edit","type":"application/atom+xml","href":"https:\/\/www.blogger.com\/feeds\/3214439820919958302\/posts\/default\/3424546643616497528"},{"rel":"self","type":"application/atom+xml","href":"https:\/\/www.blogger.com\/feeds\/3214439820919958302\/posts\/default\/3424546643616497528"},{"rel":"alternate","type":"text/html","href":"https:\/\/mahmood.razzi.my\/2019\/11\/sentiment-analysis-for-social-media.html","title":"Sentiment Analysis for Social Media"}],"author":[{"name":{"$t":"Unknown"},"email":{"$t":"noreply@blogger.com"},"gd$image":{"rel":"http://schemas.google.com/g/2005#thumbnail","width":"16","height":"16","src":"https:\/\/img1.blogblog.com\/img\/b16-rounded.gif"}}],"thr$total":{"$t":"0"}},{"id":{"$t":"tag:blogger.com,1999:blog-3214439820919958302.post-4398335092111944778"},"published":{"$t":"2019-09-06T17:32:00.018+08:00"},"updated":{"$t":"2023-01-22T12:56:53.543+08:00"},"category":[{"scheme":"http://www.blogger.com/atom/ns#","term":"*jour*"},{"scheme":"http://www.blogger.com/atom/ns#","term":"attention"},{"scheme":"http://www.blogger.com/atom/ns#","term":"lexicon"},{"scheme":"http://www.blogger.com/atom/ns#","term":"neural"}],"title":{"type":"text","$t":"Lexicon-Enhanced Attention Network Based on Text Representation for Sentiment Classification"},"content":{"type":"html","$t":"\u003Cp\u003E***\u003C\/p\u003E\u003Cp\u003EAbstract\u003C\/p\u003E\u003Cp\u003EText representation learning is an important but challenging issue for various natural language processing tasks.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003ERecently, deep learning-based representation models have achieved great success for sentiment classification.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EHowever, these existing models focus on more semantic information rather than sentiment linguistic knowledge, which provides rich sentiment information and plays a key role in sentiment analysis.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EIn this paper, we propose a lexicon-enhanced attention network (LAN) based on text representation to improve the performance of sentiment classification.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003ESpecifically, we first propose a lexicon-enhanced attention mechanism by combining the sentiment lexicon with an attention mechanism to incorporate sentiment linguistic knowledge into deep learning methods.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003ESecond, we introduce a multi-head attention mechanism in the deep neural network to interactively capture the contextual information from different representation subspaces at different positions.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EFurthermore, we stack a LAN model to build a hierarchical sentiment classification model for large-scale text.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EExtensive experiments are conducted to evaluate the effectiveness of the proposed models on four popular real-world sentiment classification datasets at both the sentence level and the document level.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EThe experimental results demonstrate that our proposed models can achieve comparable or better performance than the state-of-the-art methods.\u003C\/p\u003E\u003Cp\u003E***\u003C\/p\u003E\u003Cp\u003EKeywords: text sentiment classification; sentiment linguistic knowledge; deep learning; attention mechanis\u0026nbsp;\u003C\/p\u003E\u003Cp\u003E***\u003C\/p\u003E\u003Cp\u003E\u003Ca href=\"https:\/\/www.mdpi.com\/2076-3417\/9\/18\/3717\"\u003Ehttps:\/\/www.mdpi.com\/2076-3417\/9\/18\/3717\u003C\/a\u003E\u003C\/p\u003E\u003Cp\u003E.\u003C\/p\u003E\u003Cp\u003E\u003Cbr \/\u003E\u003C\/p\u003E"},"link":[{"rel":"replies","type":"application/atom+xml","href":"https:\/\/mahmood.razzi.my\/feeds\/4398335092111944778\/comments\/default","title":"Post Comments"},{"rel":"replies","type":"text/html","href":"https:\/\/www.blogger.com\/comment\/fullpage\/post\/3214439820919958302\/4398335092111944778","title":"0 Comments"},{"rel":"edit","type":"application/atom+xml","href":"https:\/\/www.blogger.com\/feeds\/3214439820919958302\/posts\/default\/4398335092111944778"},{"rel":"self","type":"application/atom+xml","href":"https:\/\/www.blogger.com\/feeds\/3214439820919958302\/posts\/default\/4398335092111944778"},{"rel":"alternate","type":"text/html","href":"https:\/\/mahmood.razzi.my\/2019\/09\/lexicon-enhanced-attention-network.html","title":"Lexicon-Enhanced Attention Network Based on Text Representation for Sentiment Classification"}],"author":[{"name":{"$t":"Unknown"},"email":{"$t":"noreply@blogger.com"},"gd$image":{"rel":"http://schemas.google.com/g/2005#thumbnail","width":"16","height":"16","src":"https:\/\/img1.blogblog.com\/img\/b16-rounded.gif"}}],"thr$total":{"$t":"0"}},{"id":{"$t":"tag:blogger.com,1999:blog-3214439820919958302.post-5627097545274030515"},"published":{"$t":"2019-07-17T22:28:00.007+08:00"},"updated":{"$t":"2023-01-22T22:30:35.122+08:00"},"category":[{"scheme":"http://www.blogger.com/atom/ns#","term":"*conf*"},{"scheme":"http://www.blogger.com/atom/ns#","term":"deep-learning"},{"scheme":"http://www.blogger.com/atom/ns#","term":"emotion-detection"},{"scheme":"http://www.blogger.com/atom/ns#","term":"text-analysis"},{"scheme":"http://www.blogger.com/atom/ns#","term":"textual-emotion-analysis"}],"title":{"type":"text","$t":"Gated Recurrent Neural Network Approach for Multilabel Emotion Detection in Microblogs"},"content":{"type":"html","$t":"\u003Cp\u003E***\u003C\/p\u003E\u003Cp\u003EAbstract:\u003C\/p\u003E\u003Cp\u003EPeople express their opinions and emotions freely in social media posts and online reviews that contain valuable feedback for multiple stakeholders such as businesses and political campaigns.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EManually extracting opinions and emotions from large volumes of such posts is an impossible task.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003ETherefore, automated processing of these posts to extract opinions and emotions is an important research problem.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EHowever, human emotion detection is a challenging task due to the complexity and nuanced nature.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003ETo overcome these barriers, researchers have extensively used techniques such as deep learning, distant supervision, and transfer learning.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EIn this paper, we propose a novel Pyramid Attention Network (PAN) based model for emotion detection in microblogs.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EThe main advantage of our approach is that PAN has the capability to evaluate sentences in different perspectives to capture multiple emotions existing in a single text.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EThe proposed model was evaluated on a recently released dataset and the results achieved the state-of-the-art accuracy of 58.9%.\u003C\/p\u003E\u003Cp\u003E***\u0026nbsp;\u003C\/p\u003E\u003Cp\u003E\u003Ca href=\"https:\/\/arxiv.org\/abs\/1907.07653\"\u003Ehttps:\/\/arxiv.org\/abs\/1907.07653\u003C\/a\u003E\u003C\/p\u003E\u003Cp\u003E\u003Ca href=\"https:\/\/arxiv.org\/pdf\/1907.07653.pdf\"\u003Ehttps:\/\/arxiv.org\/pdf\/1907.07653.pdf\u003C\/a\u003E\u003C\/p\u003E\u003Cp\u003E***\u003C\/p\u003E"},"link":[{"rel":"replies","type":"application/atom+xml","href":"https:\/\/mahmood.razzi.my\/feeds\/5627097545274030515\/comments\/default","title":"Post Comments"},{"rel":"replies","type":"text/html","href":"https:\/\/www.blogger.com\/comment\/fullpage\/post\/3214439820919958302\/5627097545274030515","title":"0 Comments"},{"rel":"edit","type":"application/atom+xml","href":"https:\/\/www.blogger.com\/feeds\/3214439820919958302\/posts\/default\/5627097545274030515"},{"rel":"self","type":"application/atom+xml","href":"https:\/\/www.blogger.com\/feeds\/3214439820919958302\/posts\/default\/5627097545274030515"},{"rel":"alternate","type":"text/html","href":"https:\/\/mahmood.razzi.my\/2019\/07\/gated-recurrent-neural-network-approach.html","title":"Gated Recurrent Neural Network Approach for Multilabel Emotion Detection in Microblogs"}],"author":[{"name":{"$t":"Unknown"},"email":{"$t":"noreply@blogger.com"},"gd$image":{"rel":"http://schemas.google.com/g/2005#thumbnail","width":"16","height":"16","src":"https:\/\/img1.blogblog.com\/img\/b16-rounded.gif"}}],"thr$total":{"$t":"0"}},{"id":{"$t":"tag:blogger.com,1999:blog-3214439820919958302.post-8887457997400927678"},"published":{"$t":"2019-04-26T02:15:00.008+08:00"},"updated":{"$t":"2023-01-23T02:19:37.305+08:00"},"category":[{"scheme":"http://www.blogger.com/atom/ns#","term":"*jour*"},{"scheme":"http://www.blogger.com/atom/ns#","term":"deep-learning"},{"scheme":"http://www.blogger.com/atom/ns#","term":"text-analysis"},{"scheme":"http://www.blogger.com/atom/ns#","term":"textual-emotion-analysis"},{"scheme":"http://www.blogger.com/atom/ns#","term":"unsupervised-learning"}],"title":{"type":"text","$t":"An Overview of Unsupervised Deep Feature Representation for Text Categorization"},"content":{"type":"html","$t":"\u003Cp\u003E***\u003C\/p\u003E\u003Cp\u003EAbstract:\u003C\/p\u003E\u003Cp\u003EHigh-dimensional features are extensively accessible in machine learning and computer vision areas.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EHow to learn an efficient feature representation for specific learning tasks is invariably a crucial issue.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EDue to the absence of class label information, unsupervised feature representation is exceedingly challenging.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EIn the last decade, deep learning has captured growing attention from researchers in a broad range of areas.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EMost of the deep learning methods are supervised, which is required to be fed with a large amount of accurately labeled data points.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003ENevertheless, acquiring sufficient accurately labeled data is unaffordable in numerous real-world applications, which is suggestive of the needs of unsupervised learning.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EToward this end, quite a few unsupervised feature representation approaches based on deep learning have been proposed in recent years.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EIn this paper, we attempt to provide a comprehensive overview of unsupervised deep learning methods and compare their performances in text categorization.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EOur survey starts with the autoencoder and its representative variants, including sparse autoencoder, stacked autoencoder, contractive autoencoder, denoising autoencoder, variational autoencoder, graph autoencoder, convolutional autoencoder, adversarial autoencoder, and residual autoencoder.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EAside from autoencoders, deconvolutional networks, restricted Boltzmann machines, and deep belief nets are introduced.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EThen, the reviewed unsupervised feature representation methods are compared in terms of text clustering.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EExtensive experiments in eight publicly available data sets of text documents are conducted to provide a fair test bed for the compared methods.\u003C\/p\u003E\u003Cp\u003E***\u0026nbsp;\u003C\/p\u003E\u003Cp\u003E\u003Ca href=\"https:\/\/ieeexplore.ieee.org\/document\/8700490\"\u003Ehttps:\/\/ieeexplore.ieee.org\/document\/8700490\u003C\/a\u003E\u003C\/p\u003E\u003Cp\u003E\u003Ca href=\"https:\/\/drive.google.com\/file\/d\/1kK1vhNI9uwj0AyRV8aG41osUsmtqsroJ\"\u003E1kK1vhNI9uwj0AyRV8aG41osUsmtqsroJ\u003C\/a\u003E\u003C\/p\u003E\u003Cp\u003E\u003Cbr \/\u003E\u003C\/p\u003E\u003Cp\u003E***\u003C\/p\u003E"},"link":[{"rel":"replies","type":"application/atom+xml","href":"https:\/\/mahmood.razzi.my\/feeds\/8887457997400927678\/comments\/default","title":"Post Comments"},{"rel":"replies","type":"text/html","href":"https:\/\/www.blogger.com\/comment\/fullpage\/post\/3214439820919958302\/8887457997400927678","title":"0 Comments"},{"rel":"edit","type":"application/atom+xml","href":"https:\/\/www.blogger.com\/feeds\/3214439820919958302\/posts\/default\/8887457997400927678"},{"rel":"self","type":"application/atom+xml","href":"https:\/\/www.blogger.com\/feeds\/3214439820919958302\/posts\/default\/8887457997400927678"},{"rel":"alternate","type":"text/html","href":"https:\/\/mahmood.razzi.my\/2019\/04\/an-overview-of-unsupervised-deep.html","title":"An Overview of Unsupervised Deep Feature Representation for Text Categorization"}],"author":[{"name":{"$t":"Unknown"},"email":{"$t":"noreply@blogger.com"},"gd$image":{"rel":"http://schemas.google.com/g/2005#thumbnail","width":"16","height":"16","src":"https:\/\/img1.blogblog.com\/img\/b16-rounded.gif"}}],"thr$total":{"$t":"0"}},{"id":{"$t":"tag:blogger.com,1999:blog-3214439820919958302.post-8974491188107657945"},"published":{"$t":"2018-12-27T12:55:00.005+08:00"},"updated":{"$t":"2023-01-23T13:06:58.698+08:00"},"category":[{"scheme":"http://www.blogger.com/atom/ns#","term":"*jour*"},{"scheme":"http://www.blogger.com/atom/ns#","term":"clustering"},{"scheme":"http://www.blogger.com/atom/ns#","term":"deep-learning"},{"scheme":"http://www.blogger.com/atom/ns#","term":"unsupervised-learning"}],"title":{"type":"text","$t":"Deep Self-Evolution Clustering"},"content":{"type":"html","$t":"\u003Cp\u003E***\u003C\/p\u003E\u003Cp\u003EAbstract:\u003C\/p\u003E\u003Cp\u003EClustering is a crucial but challenging task in pattern analysis and machine learning.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EExisting methods often ignore the combination between representation learning and clustering.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003ETo tackle this problem, we reconsider the clustering task from its definition to develop Deep Self-Evolution Clustering (DSEC) to jointly learn representations and cluster data.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EFor this purpose, the clustering task is recast as a binary pairwise-classification problem to estimate whether pairwise patterns are similar.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003ESpecifically, similarities between pairwise patterns are defined by the dot product between indicator features which are generated by a deep neural network (DNN).\u0026nbsp;\u003C\/p\u003E\u003Cp\u003ETo learn informative representations for clustering, clustering constraints are imposed on the indicator features to represent specific concepts with specific representations.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003ESince the ground-truth similarities are unavailable in clustering, an alternating iterative algorithm called Self-Evolution Clustering Training (SECT) is presented to select similar and dissimilar pairwise patterns and to train the DNN alternately.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EConsequently, the indicator features tend to be one-hot vectors and the patterns can be clustered by locating the largest response of the learned indicator features.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EExtensive experiments strongly evidence that DSEC outperforms current models on twelve popular image, text and audio datasets consistently.\u003C\/p\u003E\u003Cp\u003E***\u0026nbsp;\u003C\/p\u003E\u003Cp\u003E\u003Ca href=\"https:\/\/ieeexplore.ieee.org\/document\/8590804\"\u003Ehttps:\/\/ieeexplore.ieee.org\/document\/8590804\u003C\/a\u003E\u003C\/p\u003E\u003Cp\u003E\u003Ca href=\"https:\/\/drive.google.com\/file\/d\/1dUIQZEziPvasTzXb4rzl_FwBHDSBP6UG\/view?usp=share_link\"\u003E1dUIQZEziPvasTzXb4rzl_FwBHDSBP6UG\u003C\/a\u003E\u003C\/p\u003E\u003Cp\u003E***\u003C\/p\u003E"},"link":[{"rel":"replies","type":"application/atom+xml","href":"https:\/\/mahmood.razzi.my\/feeds\/8974491188107657945\/comments\/default","title":"Post Comments"},{"rel":"replies","type":"text/html","href":"https:\/\/www.blogger.com\/comment\/fullpage\/post\/3214439820919958302\/8974491188107657945","title":"0 Comments"},{"rel":"edit","type":"application/atom+xml","href":"https:\/\/www.blogger.com\/feeds\/3214439820919958302\/posts\/default\/8974491188107657945"},{"rel":"self","type":"application/atom+xml","href":"https:\/\/www.blogger.com\/feeds\/3214439820919958302\/posts\/default\/8974491188107657945"},{"rel":"alternate","type":"text/html","href":"https:\/\/mahmood.razzi.my\/2018\/12\/deep-self-evolution-clustering.html","title":"Deep Self-Evolution Clustering"}],"author":[{"name":{"$t":"Unknown"},"email":{"$t":"noreply@blogger.com"},"gd$image":{"rel":"http://schemas.google.com/g/2005#thumbnail","width":"16","height":"16","src":"https:\/\/img1.blogblog.com\/img\/b16-rounded.gif"}}],"thr$total":{"$t":"0"}},{"id":{"$t":"tag:blogger.com,1999:blog-3214439820919958302.post-3819169532107537783"},"published":{"$t":"2018-12-15T03:34:00.005+08:00"},"updated":{"$t":"2023-01-25T03:36:01.770+08:00"},"category":[{"scheme":"http://www.blogger.com/atom/ns#","term":"*jour*"},{"scheme":"http://www.blogger.com/atom/ns#","term":"deep-learning"},{"scheme":"http://www.blogger.com/atom/ns#","term":"dimensionality-reduction"},{"scheme":"http://www.blogger.com/atom/ns#","term":"text-analysis"}],"title":{"type":"text","$t":"Textual data dimensionality reduction - a deep learning approach"},"content":{"type":"html","$t":"\u003Cp\u003E***\u003C\/p\u003E\u003Cp\u003EAbstract:\u003C\/p\u003E\u003Cp\u003EThe growth of Internet has produced a high volume of natural language textual data.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003ESuch data can be sparse and may contain uninformative features which increase the dimensions of the data.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EThis high dimensionality in turn, decreases the efficiency of text mining tasks such as clustering.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003ETransforming the high dimensional data into a lower dimension is an important pre-processing step before applying clustering.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EIn this paper, dimensionality reduction method based on deep Autoencoder neural network named as DRDAE, is proposed to provide optimized and robust features for text clustering.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EDRDAE selects less correlated and salient feature space from the high dimensional feature space.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003ETo evaluate proposed algorithm, k-means is used to cluster text documents.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EThe proposed method is tested on five benchmark text datasets.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003ESimulation results demonstrate that the proposed algorithm clearly outperforms other conventional dimensionality reduction methods in the literature in terms of RI measure.\u003C\/p\u003E\u003Cp\u003E***\u0026nbsp;\u003C\/p\u003E\u003Cp\u003E\u003Ca href=\"https:\/\/link.springer.com\/article\/10.1007\/s11042-018-6900-x\"\u003Ehttps:\/\/link.springer.com\/article\/10.1007\/s11042-018-6900-x\u003C\/a\u003E\u003C\/p\u003E"},"link":[{"rel":"replies","type":"application/atom+xml","href":"https:\/\/mahmood.razzi.my\/feeds\/3819169532107537783\/comments\/default","title":"Post Comments"},{"rel":"replies","type":"text/html","href":"https:\/\/www.blogger.com\/comment\/fullpage\/post\/3214439820919958302\/3819169532107537783","title":"0 Comments"},{"rel":"edit","type":"application/atom+xml","href":"https:\/\/www.blogger.com\/feeds\/3214439820919958302\/posts\/default\/3819169532107537783"},{"rel":"self","type":"application/atom+xml","href":"https:\/\/www.blogger.com\/feeds\/3214439820919958302\/posts\/default\/3819169532107537783"},{"rel":"alternate","type":"text/html","href":"https:\/\/mahmood.razzi.my\/2018\/12\/textual-data-dimensionality-reduction.html","title":"Textual data dimensionality reduction - a deep learning approach"}],"author":[{"name":{"$t":"Unknown"},"email":{"$t":"noreply@blogger.com"},"gd$image":{"rel":"http://schemas.google.com/g/2005#thumbnail","width":"16","height":"16","src":"https:\/\/img1.blogblog.com\/img\/b16-rounded.gif"}}],"thr$total":{"$t":"0"}},{"id":{"$t":"tag:blogger.com,1999:blog-3214439820919958302.post-3400439051030014788"},"published":{"$t":"2018-08-12T02:10:00.006+08:00"},"updated":{"$t":"2023-01-21T02:12:21.827+08:00"},"category":[{"scheme":"http://www.blogger.com/atom/ns#","term":"*jour*"},{"scheme":"http://www.blogger.com/atom/ns#","term":"seed-lexicon"},{"scheme":"http://www.blogger.com/atom/ns#","term":"sentiment-lexicon"}],"title":{"type":"text","$t":"Automatic Approach of Sentiment Lexicon Generation for Mobile Shopping Reviews"},"content":{"type":"html","$t":"\u003Cp\u003E***\u003C\/p\u003E\u003Cp\u003EAbstract:\u003C\/p\u003E\u003Cp\u003EThe dramatic increase in the use of smartphones has allowed people to comment on various products at any time.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EThe analysis of the sentiment of users’ product reviews largely depends on the quality of sentiment lexicons.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EThus, the generation of high-quality sentiment lexicons is a critical topic.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EIn this paper, we propose an automatic approach for constructing a domain-specific sentiment lexicon by considering the relationship between sentiment words and product features in mobile shopping reviews.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EThe approach first selects sentiment words and product features from original reviews and mines the relationship between them using an improved pointwise mutual information algorithm.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003ESecond, sentiment words that are related to mobile shopping are clustered into categories to form sentiment dimensions.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EAt each sentiment dimension, each sentiment word can take the value of 0 or 1, where 1 indicates that the word belongs to a particular category whereas 0 indicates that it does not belong to that category.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EThe generated lexicon is evaluated by constructing a sentiment classification task using several product reviews written in both Chinese and English.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003ETwo popular non-domain-specific sentiment lexicons as well as state-of-the-art machine-learning and deep-learning models are chosen as benchmarks, and the experimental results show that our sentiment lexicons outperform the benchmarks with statistically significant differences, thus proving the effectiveness of the proposed approach.\u003C\/p\u003E\u003Cp\u003E***\u0026nbsp;\u003C\/p\u003E\u003Cp\u003E\u003Ca href=\"https:\/\/www.hindawi.com\/journals\/wcmc\/2018\/9839432\/\"\u003Ehttps:\/\/www.hindawi.com\/journals\/wcmc\/2018\/9839432\/\u003C\/a\u003E\u003C\/p\u003E\u003Cp\u003E***\u003C\/p\u003E\u003Cp\u003E\u003Cbr \/\u003E\u003C\/p\u003E"},"link":[{"rel":"replies","type":"application/atom+xml","href":"https:\/\/mahmood.razzi.my\/feeds\/3400439051030014788\/comments\/default","title":"Post Comments"},{"rel":"replies","type":"text/html","href":"https:\/\/www.blogger.com\/comment\/fullpage\/post\/3214439820919958302\/3400439051030014788","title":"0 Comments"},{"rel":"edit","type":"application/atom+xml","href":"https:\/\/www.blogger.com\/feeds\/3214439820919958302\/posts\/default\/3400439051030014788"},{"rel":"self","type":"application/atom+xml","href":"https:\/\/www.blogger.com\/feeds\/3214439820919958302\/posts\/default\/3400439051030014788"},{"rel":"alternate","type":"text/html","href":"https:\/\/mahmood.razzi.my\/2018\/08\/automatic-approach-of-sentiment-lexicon.html","title":"Automatic Approach of Sentiment Lexicon Generation for Mobile Shopping Reviews"}],"author":[{"name":{"$t":"Unknown"},"email":{"$t":"noreply@blogger.com"},"gd$image":{"rel":"http://schemas.google.com/g/2005#thumbnail","width":"16","height":"16","src":"https:\/\/img1.blogblog.com\/img\/b16-rounded.gif"}}],"thr$total":{"$t":"0"}},{"id":{"$t":"tag:blogger.com,1999:blog-3214439820919958302.post-5434842447601358416"},"published":{"$t":"2018-06-28T13:13:00.003+08:00"},"updated":{"$t":"2023-01-22T13:21:45.972+08:00"},"category":[{"scheme":"http://www.blogger.com/atom/ns#","term":"*conf*"},{"scheme":"http://www.blogger.com/atom/ns#","term":"deep-learning"},{"scheme":"http://www.blogger.com/atom/ns#","term":"neural"},{"scheme":"http://www.blogger.com/atom/ns#","term":"text-analysis"},{"scheme":"http://www.blogger.com/atom/ns#","term":"textual-emotion-analysis"}],"title":{"type":"text","$t":"Study of text emotion analysis based on deep learning"},"content":{"type":"html","$t":"\u003Cp\u003E***\u003C\/p\u003E\u003Cp\u003EAbstract:\u003C\/p\u003E\u003Cp\u003EIn traditional sentiment classification methods, sentiment-based methods rely heavily on the quality and coverage of sentiment lexicons, whereas machine-based approaches rely on features of manual construction and decimation.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EIn recent years, deep learning technology has made great progress in the field of natural language processing, depth model has more powerful skills.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EThis article focuses on several commonly used deep learning models for textual affective classification and compares their strengths and weaknesses.\u003C\/p\u003E\u003Cp\u003E***\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EKeywords:\u003C\/p\u003E\u003Cp\u003Edeep learning, convolutional neural networks, recurrent neural networks, short and long-term memory recurrent neural networks\u003C\/p\u003E\u003Cp\u003E***\u003C\/p\u003E\u003Cp\u003E\u003Ca href=\"https:\/\/ieeexplore.ieee.org\/document\/8398170\/\"\u003Ehttps:\/\/ieeexplore.ieee.org\/document\/8398170\/\u003C\/a\u003E\u003C\/p\u003E\u003Cp\u003E\u003Cbr \/\u003E\u003C\/p\u003E\u003Cp\u003E***\u003C\/p\u003E\u003Cp\u003E\u003Cbr \/\u003E\u003C\/p\u003E"},"link":[{"rel":"replies","type":"application/atom+xml","href":"https:\/\/mahmood.razzi.my\/feeds\/5434842447601358416\/comments\/default","title":"Post Comments"},{"rel":"replies","type":"text/html","href":"https:\/\/www.blogger.com\/comment\/fullpage\/post\/3214439820919958302\/5434842447601358416","title":"0 Comments"},{"rel":"edit","type":"application/atom+xml","href":"https:\/\/www.blogger.com\/feeds\/3214439820919958302\/posts\/default\/5434842447601358416"},{"rel":"self","type":"application/atom+xml","href":"https:\/\/www.blogger.com\/feeds\/3214439820919958302\/posts\/default\/5434842447601358416"},{"rel":"alternate","type":"text/html","href":"https:\/\/mahmood.razzi.my\/2018\/06\/study-of-text-emotion-analysis-based-on.html","title":"Study of text emotion analysis based on deep learning"}],"author":[{"name":{"$t":"Unknown"},"email":{"$t":"noreply@blogger.com"},"gd$image":{"rel":"http://schemas.google.com/g/2005#thumbnail","width":"16","height":"16","src":"https:\/\/img1.blogblog.com\/img\/b16-rounded.gif"}}],"thr$total":{"$t":"0"}},{"id":{"$t":"tag:blogger.com,1999:blog-3214439820919958302.post-5390419986130317264"},"published":{"$t":"2017-12-31T22:10:00.010+08:00"},"updated":{"$t":"2023-01-22T22:13:27.483+08:00"},"category":[{"scheme":"http://www.blogger.com/atom/ns#","term":"*conf*"},{"scheme":"http://www.blogger.com/atom/ns#","term":"deep-learning"},{"scheme":"http://www.blogger.com/atom/ns#","term":"emotion-analysis"}],"title":{"type":"text","$t":"EmoNet: Fine-Grained Emotion Detection with Gated Recurrent Neural Networks"},"content":{"type":"html","$t":"\u003Cp\u003E***\u003C\/p\u003E\u003Cp\u003EAccurate detection of emotion from natural language has applications ranging from building emotional chatbots to better understanding individuals and their lives.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EHowever, progress on emotion detection has been hampered by the absence of large labeled datasets.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EIn this work, we build a very large dataset for fine-grained emotions and develop deep learning models on it.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EWe achieve a new state-of-the-art on 24 fine-grained types of emotions (with an average accuracy of 87.58%).\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EWe also extend the task beyond emotion types to model Robert Plutchik’s 8 primary emotion dimensions, acquiring a superior accuracy of 95.68%.\u003C\/p\u003E\u003Cp\u003E\u003Cbr \/\u003E\u003C\/p\u003E\u003Cp\u003E***\u0026nbsp;\u003C\/p\u003E\u003Cp\u003E\u003Ca href=\"https:\/\/aclanthology.org\/P17-1067\/\"\u003Ehttps:\/\/aclanthology.org\/P17-1067\/\u003C\/a\u003E\u003C\/p\u003E\u003Cp\u003E\u003Ca href=\"https:\/\/aclanthology.org\/P17-1067.pdf\"\u003Ehttps:\/\/aclanthology.org\/P17-1067.pdf\u003C\/a\u003E\u003C\/p\u003E\u003Cp\u003E***\u003C\/p\u003E\u003Cp\u003E\u003Cbr \/\u003E\u003C\/p\u003E\u003Cp\u003E\u003Cbr \/\u003E\u003C\/p\u003E"},"link":[{"rel":"replies","type":"application/atom+xml","href":"https:\/\/mahmood.razzi.my\/feeds\/5390419986130317264\/comments\/default","title":"Post Comments"},{"rel":"replies","type":"text/html","href":"https:\/\/www.blogger.com\/comment\/fullpage\/post\/3214439820919958302\/5390419986130317264","title":"0 Comments"},{"rel":"edit","type":"application/atom+xml","href":"https:\/\/www.blogger.com\/feeds\/3214439820919958302\/posts\/default\/5390419986130317264"},{"rel":"self","type":"application/atom+xml","href":"https:\/\/www.blogger.com\/feeds\/3214439820919958302\/posts\/default\/5390419986130317264"},{"rel":"alternate","type":"text/html","href":"https:\/\/mahmood.razzi.my\/2017\/12\/emonet-fine-grained-emotion-detection.html","title":"EmoNet: Fine-Grained Emotion Detection with Gated Recurrent Neural Networks"}],"author":[{"name":{"$t":"Unknown"},"email":{"$t":"noreply@blogger.com"},"gd$image":{"rel":"http://schemas.google.com/g/2005#thumbnail","width":"16","height":"16","src":"https:\/\/img1.blogblog.com\/img\/b16-rounded.gif"}}],"thr$total":{"$t":"0"}},{"id":{"$t":"tag:blogger.com,1999:blog-3214439820919958302.post-9106756408123314765"},"published":{"$t":"2017-06-08T00:19:00.007+08:00"},"updated":{"$t":"2023-01-22T12:53:21.607+08:00"},"category":[{"scheme":"http://www.blogger.com/atom/ns#","term":"*conf*"},{"scheme":"http://www.blogger.com/atom/ns#","term":"convolutional"},{"scheme":"http://www.blogger.com/atom/ns#","term":"long-short-term-memory"}],"title":{"type":"text","$t":"Deep Learning approach for sentiment analysis of short texts"},"content":{"type":"html","$t":"\u003Cp\u003E***\u003C\/p\u003E\u003Cp\u003EAbstract:\u003C\/p\u003E\u003Cp\u003EUnstructured text data produced on the internet grows rapidly, and sentiment analysis for short texts becomes a challenge because of the limit of the contextual information they usually contain.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003ELearning good vector representations for sentences is a challenging task and an ongoing research area.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EMoreover, learning long-term dependencies with gradient descent is difficult in neural network language model because of the vanishing gradients problem.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003ENatural Language Processing (NLP) systems traditionally treat words as discrete atomic symbols; the model can leverage small amounts of information regarding the relationship between the individual symbols.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EIn this paper, we propose ConvLstm, neural network architecture that employs Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) on top of pre-trained word vectors.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EIn our experiments, ConvLstm exploit LSTM as a substitute of pooling layer in CNN to reduce the loss of detailed local information and capture long term dependencies in sequence of sentences.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EWe validate the proposed model on two sentiment datasets IMDB, and Stanford Sentiment Treebank (SSTb).\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EEmpirical results show that ConvLstm achieved comparable performances with less parameters on sentiment analysis tasks.\u003C\/p\u003E\u003Cp\u003E***\u003C\/p\u003E\u003Cp\u003E\u003Ca href=\"https:\/\/ieeexplore.ieee.org\/document\/7942788\"\u003Ehttps:\/\/ieeexplore.ieee.org\/document\/7942788\u003C\/a\u003E\u003C\/p\u003E\u003Cp\u003E***\u003C\/p\u003E"},"link":[{"rel":"replies","type":"application/atom+xml","href":"https:\/\/mahmood.razzi.my\/feeds\/9106756408123314765\/comments\/default","title":"Post Comments"},{"rel":"replies","type":"text/html","href":"https:\/\/www.blogger.com\/comment\/fullpage\/post\/3214439820919958302\/9106756408123314765","title":"0 Comments"},{"rel":"edit","type":"application/atom+xml","href":"https:\/\/www.blogger.com\/feeds\/3214439820919958302\/posts\/default\/9106756408123314765"},{"rel":"self","type":"application/atom+xml","href":"https:\/\/www.blogger.com\/feeds\/3214439820919958302\/posts\/default\/9106756408123314765"},{"rel":"alternate","type":"text/html","href":"https:\/\/mahmood.razzi.my\/2017\/06\/deep-learning-approach-for-sentiment.html","title":"Deep Learning approach for sentiment analysis of short texts"}],"author":[{"name":{"$t":"Unknown"},"email":{"$t":"noreply@blogger.com"},"gd$image":{"rel":"http://schemas.google.com/g/2005#thumbnail","width":"16","height":"16","src":"https:\/\/img1.blogblog.com\/img\/b16-rounded.gif"}}],"thr$total":{"$t":"0"}},{"id":{"$t":"tag:blogger.com,1999:blog-3214439820919958302.post-4642660906158312583"},"published":{"$t":"2016-05-07T18:09:00.008+08:00"},"updated":{"$t":"2023-09-02T19:57:47.267+08:00"},"category":[{"scheme":"http://www.blogger.com/atom/ns#","term":"*conf*"},{"scheme":"http://www.blogger.com/atom/ns#","term":"lexicon-construction"}],"title":{"type":"text","$t":"Empath: Understanding Topic Signals in Large-Scale Text"},"content":{"type":"html","$t":"\u003Cp\u003E***\u003C\/p\u003E\u003Cp\u003EAbstract:\u003C\/p\u003E\u003Cp\u003EHuman language is colored by a broad range of topics, but existing text analysis tools only focus on a small number of them.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EWe present Empath, a tool that can generate and validate new lexical categories on demand from a small set of seed terms (like \"bleed\" and \"punch\" to generate the category violence).\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EEmpath draws connotations between words and phrases by deep learning a neural embedding across more than 1.8 billion words of modern fiction.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EGiven a small set of seed words that characterize a category, Empath uses its neural embedding to discover new related terms, then validates the category with a crowd-powered filter.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EEmpath also analyzes text across 200 built-in, pre-validated categories we have generated from common topics in our web dataset, like neglect, government, and social media.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EWe show that Empath's data-driven, human validated categories are highly correlated (r=0.906) with similar categories in LIWC.\u003C\/p\u003E\u003Cp\u003E***\u003C\/p\u003E\u003Cp\u003E\u003Ca href=\"https:\/\/dl.acm.org\/doi\/10.1145\/2858036.2858535\"\u003Ehttps:\/\/dl.acm.org\/doi\/10.1145\/2858036.2858535\u003C\/a\u003E\u003C\/p\u003E\u003Cp\u003E\u003Ca href=\"https:\/\/arxiv.org\/pdf\/1602.06979.pdf\"\u003Ehttps:\/\/arxiv.org\/pdf\/1602.06979.pdf\u003C\/a\u003E\u003C\/p\u003E\u003Cp\u003E***\u003C\/p\u003E\u003Cp\u003E\u003Cbr \/\u003E\u003C\/p\u003E\u003Cp\u003E***\u0026nbsp;\u003C\/p\u003E"},"link":[{"rel":"replies","type":"application/atom+xml","href":"https:\/\/mahmood.razzi.my\/feeds\/4642660906158312583\/comments\/default","title":"Post Comments"},{"rel":"replies","type":"text/html","href":"https:\/\/www.blogger.com\/comment\/fullpage\/post\/3214439820919958302\/4642660906158312583","title":"0 Comments"},{"rel":"edit","type":"application/atom+xml","href":"https:\/\/www.blogger.com\/feeds\/3214439820919958302\/posts\/default\/4642660906158312583"},{"rel":"self","type":"application/atom+xml","href":"https:\/\/www.blogger.com\/feeds\/3214439820919958302\/posts\/default\/4642660906158312583"},{"rel":"alternate","type":"text/html","href":"https:\/\/mahmood.razzi.my\/2016\/05\/empath-understanding-topic-signals-in.html","title":"Empath: Understanding Topic Signals in Large-Scale Text"}],"author":[{"name":{"$t":"Unknown"},"email":{"$t":"noreply@blogger.com"},"gd$image":{"rel":"http://schemas.google.com/g/2005#thumbnail","width":"16","height":"16","src":"https:\/\/img1.blogblog.com\/img\/b16-rounded.gif"}}],"thr$total":{"$t":"0"}},{"id":{"$t":"tag:blogger.com,1999:blog-3214439820919958302.post-4617070735560070499"},"published":{"$t":"2015-11-29T17:46:00.007+08:00"},"updated":{"$t":"2023-01-22T17:49:08.650+08:00"},"category":[{"scheme":"http://www.blogger.com/atom/ns#","term":"*blog*"},{"scheme":"http://www.blogger.com/atom/ns#","term":"deep-learning"},{"scheme":"http://www.blogger.com/atom/ns#","term":"text-analysis"},{"scheme":"http://www.blogger.com/atom/ns#","term":"textual-emotion-analysis"}],"title":{"type":"text","$t":"Emotion Detection and Recognition from Text Using Deep Learning"},"content":{"type":"html","$t":"\u003Cp\u003E***\u003C\/p\u003E\u003Cp\u003EWhy emotion detection?\u003C\/p\u003E\u003Cp\u003EEmotion Detection and Recognition from text is a recent field of research that is closely related to Sentiment Analysis. Sentiment Analysis aims to detect positive, neutral, or negative feelings from text, whereas Emotion Analysis aims to detect and recognize types of feelings through the expression of texts, such as anger, disgust, fear, happiness, sadness, and surprise. Emotion detection may have useful applications, such as:\u003C\/p\u003E\u003Cp\u003E\u003Cbr \/\u003E\u003C\/p\u003E\u003Cp\u003EGauging how happy our citizens are. Different indexes have different definitions; most evolve around economic, environmental, health, and social factors. Since the mid-2000s, Government and organizations around the world are paying increasing attention to the happiness index.\u003C\/p\u003E\u003Cp\u003EThe Happy Planet Index (HPI) (news, TED talk). This metric is defined as the overall index scores that rank countries based on their efficiency, as well as how many long and happy lives each country produces per unit of environmental output. This is unusual because the majority of indexes are based upon economic measures.\u003C\/p\u003E\u003Cp\u003ESocietal Wellbeing metrics. The UK government measures people’s wellbeing; their statistics can be found here. Other countries and cities such as Seattle, Dubai, and South Korea, have similar measures.\u003C\/p\u003E\u003Cp\u003EPervasive computing, to serve the individual better. This may include suggesting help when anxiety is detected through speech, or to check the tone of an email before sending it out.\u003C\/p\u003E\u003Cp\u003EUnderstanding the consumer. Improving perception of a customer with the ultimate goal to increase brand reputation and sales.\u003C\/p\u003E\u003Cp\u003EHow?\u003C\/p\u003E\u003Cp\u003EThere are 6 emotion categories that are widely used to describe humans’ basic emotions, based on facial expression [1]: anger, disgust, fear, happiness, sadness and surprise. These are mainly associated with negative sentiment, with “Surprise” being the most ambiguous, as it can be associated with either positive or negative feelings. Interestingly, the number of basic human emotions has been recently “reduced”, or rather re-categorized, to just 4; happiness, sadness, fear\/surprise, and anger\/disgust [2]. It is surprising to many that we only have 4 basic emotions. For the sake of simplicity for this code story, we will use the more widely-used 6 emotions. (Other classifications of emotions can be found here.) The question remains, however, how much of an emotion we can convey via text? This is especially interesting since facial expression and voice intonation convey over 70% of the intended feelings in spoken language.\u003C\/p\u003E\u003Cp\u003E\u003Cbr \/\u003E\u003C\/p\u003E\u003Cp\u003EIn any recognition task, the 3 most common approaches are rule-based, statistic-based and hybrid, and their use depends on factors such as availability of data, domain expertise, and domain specificity. In the case of sentiment analysis, this task can be tackled using lexicon-based methods, machine learning, or a concept-level approach [3]. Here, we are exploring how we can achieve this task via a machine learning approach, specifically using the deep learning technique.\u003C\/p\u003E\u003Cp\u003E\u003Cbr \/\u003E\u003C\/p\u003E\u003Cp\u003EIs It Possible?\u003C\/p\u003E\u003Cp\u003EOne of the biggest challenges in determining emotion is the context-dependence of emotions within text. A phrase can have element of anger without using the word “anger” or any of its synonyms. For example, the phrase “Shut up!”. Another challenge is the difficulty that other components of NLP are facing, such as word-sense disambiguation and co-reference resolution. It is difficult to anticipate the success rate of machine learning approach without first trying.\u003C\/p\u003E\u003Cp\u003E\u003Cbr \/\u003E\u003C\/p\u003E\u003Cp\u003EData:\u003C\/p\u003E\u003Cp\u003EAnother challenge in emotion detection is the lack of a labelled emotion database to enable active innovation. Currently, few publicly accessible databases are available. The 2 most commonly used databases are ISEAR, which contains 2500 sentences, with 5 categories of emotions (it lacks “Surprise”). The SemEval 2007 [4] Affective Text database consists of 250 sentences annotated with 6 categories of emotions, with another 1000 sentences as test data. This database is primarily designed for exploration of the connection between lexical semantics and emotions. If we were to encourage progress in this area, a more comprehensive database with more observations may be required, especially if we are to tackle this task via a machine learning approach.\u003C\/p\u003E\u003Cp\u003E\u003Cbr \/\u003E\u003C\/p\u003E\u003Cp\u003EText is extracted from a variety of sources as described below, and people can be crowd sourced to perform labelling using Mechanical Turk. A process, inspired by a DARPA [5,6] translation project, which is also crowd-sourced, is put in place to validate the accuracy of labelling.\u003C\/p\u003E\u003Cp\u003E\u003Cbr \/\u003E\u003C\/p\u003E\u003Cp\u003E***\u0026nbsp;\u003C\/p\u003E\u003Cp\u003E\u003Ca href=\"https:\/\/devblogs.microsoft.com\/cse\/2015\/11\/29\/emotion-detection-and-recognition-from-text-using-deep-learning\/\"\u003Ehttps:\/\/devblogs.microsoft.com\/cse\/2015\/11\/29\/emotion-detection-and-recognition-from-text-using-deep-learning\/\u003C\/a\u003E\u003C\/p\u003E\u003Cp\u003E***\u003C\/p\u003E"},"link":[{"rel":"replies","type":"application/atom+xml","href":"https:\/\/mahmood.razzi.my\/feeds\/4617070735560070499\/comments\/default","title":"Post Comments"},{"rel":"replies","type":"text/html","href":"https:\/\/www.blogger.com\/comment\/fullpage\/post\/3214439820919958302\/4617070735560070499","title":"0 Comments"},{"rel":"edit","type":"application/atom+xml","href":"https:\/\/www.blogger.com\/feeds\/3214439820919958302\/posts\/default\/4617070735560070499"},{"rel":"self","type":"application/atom+xml","href":"https:\/\/www.blogger.com\/feeds\/3214439820919958302\/posts\/default\/4617070735560070499"},{"rel":"alternate","type":"text/html","href":"https:\/\/mahmood.razzi.my\/2015\/11\/emotion-detection-and-recognition-from.html","title":"Emotion Detection and Recognition from Text Using Deep Learning"}],"author":[{"name":{"$t":"Unknown"},"email":{"$t":"noreply@blogger.com"},"gd$image":{"rel":"http://schemas.google.com/g/2005#thumbnail","width":"16","height":"16","src":"https:\/\/img1.blogblog.com\/img\/b16-rounded.gif"}}],"thr$total":{"$t":"0"}}]}}