UNIBA: Sentiment Analysis of English Tweets Combining Micro-blogging, Lexicon and Semantic Features

Proceedings of the 9th International Workshop on Semantic Evaluation (SemEval 2015), pages 595–600, Denver, Colorado, June 4-5, 2015. c⃝2015 Association for Computational Linguistics UNIBA: Sentiment Analysis of English Tweets Combining Micro-blogging, Lexicon and Semantic Features Pierpaolo Basile and Nicole Novielli Department of Computer Science, University of Bari Aldo Moro Via, E. Orabona, 4 - 70125 Bari (Italy) {pierpaolo.basile,nicole.novielli}@uniba.it Abstract This paper describes the UNIBA team partic- ipation in the Sentiment Analysis in Twitter task (Task 10) at SemEval-2015. We propose a supervised approach relying on keyword, lex- icon and micro-blogging features as well as representation of tweets in a word space. 1 Introduction Sentiment analysis is the study of the subjectivity and polarity (positive vs. negative) of a text (Pang and Lee, 2008). With the worldwide diffusion of social media, a huge amount of textual data has been made available, thus attracting the interest of researchers in this domain (Rosenthal et al., 2014). Sentiment analysis on such informal texts poses new challenges due to the presence of slang, misspelled words and micro-blogging features such as hash- tags or links and traditional approaches may not be successfully exploited in this domain. Previous re- search has successfully exploited approaches based on lexical and micro-blogging features (Mohammad et al., 2013). In this study, we investigate a su- pervised approach including three kinds of features based on keywords and micro-blogging properties of tweets, sentiment lexicons and semantics. Rather than using word-sense disambiguation (Miura et al., 2014), we represent tweets in a distributional seman- tic model (DSM) (Vanzo et al., 2014), which is able to learn the context of usage of words analysing co- occurrences in large corpora. This paper describes our participation at the Se- mEval 2015 Sentiment Analysis in Twitter task (Rosenthal et al., 2015). We discuss methods and results of our experimental study for the overall po- larity classification of tweets (message level sub- task B). The Sentiment Analysis task focuses on En- glish tweets. Data provided for training are anno- tated according to the overall polarity of each tweet (i.e., ’negative’, ’positive’ or ’neutral’). The sys- tem evaluation is performed on different test sets. In particular, the rank of the systems is calculated on the offical Twitter 2015 test set. Further evalu- ation is performed on a progress set including test instances from the previous edition of the task, to allow comparision with previous studies (Rosenthal et al., 2014). We build a supervised system based on our sentiment classifier for Italian tweets, which ranked 1st in both the polarity and subjectivity tasks at Evalita 2014 (Basile and Novielli, 2014). The paper is structured as follows: we introduce our system and report the details about features in Section 2. We describe the evaluation and the sys- tem setup in Section 3. We conclude by reporting results and discussion in Section 4. 2 System Description Our system is built upon our classifier for senti- ment analysis of Italian tweets (Basile and Novielli, 2014). We adopt a supervised approach using Sup- port Vector Machine …

Content truncated to 500 words