TwiSE at SemEval-2016 Task 4: Twitter Sentiment Classification

TL;DR

The TwiSE team developed and optimized ensemble and linear models for Twitter sentiment classification across multiple subtasks, achieving competitive rankings in the SemEval-2016 challenge.

Contribution

This work introduces a systematic feature generation and validation process, along with ensemble learning strategies, for improved Twitter sentiment analysis.

Findings

Achieved top rankings in subtasks C and D

Validated diverse feature sets for sentiment evaluation

Demonstrated effectiveness of ensemble learning approaches

Abstract

This paper describes the participation of the team "TwiSE" in the SemEval 2016 challenge. Specifically, we participated in Task 4, namely "Sentiment Analysis in Twitter" for which we implemented sentiment classification systems for subtasks A, B, C and D. Our approach consists of two steps. In the first step, we generate and validate diverse feature sets for twitter sentiment evaluation, inspired by the work of participants of previous editions of such challenges. In the second step, we focus on the optimization of the evaluation measures of the different subtasks. To this end, we examine different learning strategies by validating them on the data provided by the task organisers. For our final submissions we used an ensemble learning approach (stacked generalization) for Subtask A and single linear models for the rest of the subtasks. In the official leaderboard we were ranked 9/35, 8/19, 1/11 and 2/14 for subtasks A, B, C and D respectively.\footnote{We make the code available for research purposes at \url{https://github.com/balikasg/SemEval2016-Twitter\_Sentiment\_Evaluation}.}