Media

How many emotions do humans have?

What do you think?

Sentiment analysis of short informal texts

***

Abstract:

We describe a state-of-the-art sentiment analysis system that detects (a) the sentiment of short informal textual messages such as tweets and SMS (message-level task) and (b) the sentiment of a word or a phrase within a message (term-level task). 

The system is based on a supervised statistical text classification approach leveraging a variety of surface-form, semantic, and sentiment features. 

The sentiment features are primarily derived from novel high-coverage tweet-specific sentiment lexicons. 

These lexicons are automatically generated from tweets with sentiment-word hashtags and from tweets with emoticons. 

To adequately capture the sentiment of words in negated contexts, a separate sentiment lexicon is generated for negated words.

The system ranked first in the SemEval-2013 shared task 'Sentiment Analysis in Twitter' (Task 2), obtaining an F-score of 69.02 in the message-level task and 88.93 in the term-level task. 

Post-competition improvements boost the performance to an F-score of 70.45 (message-level task) and 89.50 (term-level task). 

The system also obtains state-of-the-art performance on two additional datasets: the SemEval-2013 SMS test set and a corpus of movie review excerpts. 

The ablation experiments demonstrate that the use of the automatically generated lexicons results in performance gains of up to 6.5 absolute percentage points.

*** 

https://dl.acm.org/doi/10.5555/2693068.2693087

https://www.jair.org/index.php/jair/article/view/10896/25984

***

No comments: