SentiSys at SemEval-2016 Task 4: Feature-Based System for Sentiment Analysis in Twitter

Proceedings of SemEval-2016, pages 190–197, San Diego, California, June 16-17, 2016. c⃝2016 Association for Computational Linguistics SentiSys at SemEval-2016 Task 4: Feature-Based System for Sentiment Analysis in Twitter Hussam Hamdan Aix-Marseille University hamdan.hussam@gmail.com Abstract This paper describes our sentiment analysis system which has been built for Sentiment Analysis in Twitter Task of SemEval-2016. We have used a Logistic Regression classifier with different groups of features. This sys- tem is an improvement to our previous sys- tem Lsislif in Semeval-2015 after removing some features and adding new features ex- tracted from a new automatic constructed sen- timent lexicon. 1 Introduction Sentiment analysis in Twitter is different from doc- ument level sentiment analysis. Normally, in docu- ment level, each document is classified as positive or negative, the document is long enough to obtain a good representation using only the existing words (bag-of-words). For example, in movie reviews we can get f-score of 85% using bag-of-words repre- sentation with SVM classifier while in Twitter it is about 60% according to our experiments in previ- ous SemEval workshops. This lower performance in Twitter domain is not surprising if we know the limitations of such task when applied to Twitter: • The size of a tweet is limited to 140 characters which leads to sparseness where the tweets do not provide enough word co-occurrence. • The informal language and non-standard ex- pressions. • The numerous spelling errors. For dealing with the previous limitations, we have decided to extend the bag-of-words representation. Therefore, many group of features have been ex- tracted. Uni-gram, bi-gram and 3-grams of words features to capture the text of tweet and the con- text. Negation features to handle the negated con- text. Sentiment lexicons features can help the clas- sification because it contains positive and negative words which can add a useful information about the polarity of a tweet, they also contain a lot of terms which may not appear in the training data which can be very useful. Semantic features as Brown clusters can also give a rich representation which can be use- ful for reducing the sparsity. For evaluating our system, we have participated in SemEval-2016 competition for sentiment analysis in Twitter (message polarity subtask A)1 (Nakov et al., 2016). Our system has been ranked six over 34, this system is derived from our previous system LsisLif which has been ranked third in SemEval-2015. The rest of this chapter is organized as follows. Section 2 presents the problem formulation. Sec- tion 3 gives an overview of our proposed approach. The features we extracted for training the classifier are presented in Section 4. Our experiments are de- scribed in Section 5. The related work is presented in Section 6. The conclusion and future work are presented in Section 7. 2 Problem Formulation Let T = t1, t2, .., tn be a collection of n tweets. Each tweet ti will be represented by a subset of all 1http://alt.qcri.org/semeval2016/task4/ 190 possible features F = f1, f2, .., fm that can appear in ti. …

Content truncated to 500 words