TwiSE at SemEval-2016 Task 4: Twitter Sentiment Classification

Proceedings of SemEval-2016, pages 85–91, San Diego, California, June 16-17, 2016. c⃝2016 Association for Computational Linguistics TwiSE at SemEval-2016 Task 4: Twitter Sentiment Classification Georgios Balikas and Massih-Reza Amini University of Grenoble-Alpes firstnane.lastname@imag.fr 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. The code can be found at https://github.com/ balikasg/SemEval2016-Twitter_ Sentiment_Evaluation. 1 Introduction During the last decade, short-text communication forms, such as Twitter microblogging, have been widely adopted and have become ubiquitous. Us- ing such forms of communication, users share a va- riety of information. However, information concern- ing one’s sentiment on the world around her has at- tracted a lot of research interest (Nakov et al., 2016; Rosenthal et al., 2015). Working with such short, informal text spans poses a number of different challenges to the Natu- ral Language Processing (NLP) and Machine Learn- ing (ML) communities. Those challenges arise from the vocabulary used (slang, abbreviations, emojis) (Maas et al., 2011), the short size, and the complex linguistic phenomena such as sarcasm (Rajadesin- gan et al., 2015) that often occur. We present, here, our participation in Task 4 of SemEval 2016 (Nakov et al., 2016), namely Senti- ment Analysis in Twitter. Task 4 comprised five dif- ferent subtasks: Subtask A: Message Polarity Clas- sification, Subtask B: Tweet classification according to a two-point scale, Subtask C: Tweet classification according to a five-point scale, Subtask D: Tweet quantification according to a two-point scale, and Subtask E: Tweet quantification according to a five- point scale. We participated in the first four subtasks under the team name “TwiSE” (Twitter Sentiment Evaluation). Our work consists of two steps: the preprocessing and feature extraction step, where we implemented and tested different feature sets pro- posed by participants of the previous editions of Se- mEval challenges (Tang et al., 2014; Kiritchenko et al., 2014a), and the learning step, where we inves- tigated and optimized the performance of different learning strategies for the SemEval subtasks. For Subtask A we submitted the output of a stacked gen- eralization (Wolpert, 1992) ensemble learning ap- proach using the probabilistic outputs of a set of lin- ear models as base models, whereas for the rest of …

Content truncated to 500 words