SemEval-2017 Task 4: Sentiment Analysis in Twitter

TL;DR

This paper reports on the fifth year of the SemEval Twitter sentiment analysis task, expanding to Arabic and incorporating user profile data, with high participation and multiple subtasks on sentiment detection and quantification.

Contribution

It introduces Arabic language support and user profile information into the Twitter sentiment analysis task, building on previous years' subtasks and data.

Findings

High participation with 48 teams

Successful integration of Arabic language data

Enhanced subtasks with user profile information

Abstract

This paper describes the fifth year of the Sentiment Analysis in Twitter task. SemEval-2017 Task 4 continues with a rerun of the subtasks of SemEval-2016 Task 4, which include identifying the overall sentiment of the tweet, sentiment towards a topic with classification on a two-point and on a five-point ordinal scale, and quantification of the distribution of sentiment towards a topic across a number of tweets: again on a two-point and on a five-point ordinal scale. Compared to 2016, we made two changes: (i) we introduced a new language, Arabic, for all subtasks, and (ii)~we made available information from the profiles of the Twitter users who posted the target tweets. The task continues to be very popular, with a total of 48 teams participating this year.