IIIT-H at SemEval 2015: Twitter Sentiment Analysis – The Good, the Bad and the Neutral!

Proceedings of the 9th International Workshop on Semantic Evaluation (SemEval 2015), pages 520–526, Denver, Colorado, June 4-5, 2015. c⃝2015 Association for Computational Linguistics IIIT-H at SemEval 2015: Twitter Sentiment Analysis The good, the bad and the neutral! Ayushi Dalmia, Manish Gupta∗, Vasudeva Varma Search and Information Extraction Lab International Institute of Information Technology, Hyderabad {ayushi.dalmia@research.iiit.ac.in, manish.gupta@iiit.ac.in, vv@iiit.ac.in } Abstract This paper describes the system that was sub- mitted to SemEval2015 Task 10: Sentiment Analysis in Twitter. We participated in Sub- task B: Message Polarity Classification. The task is a message level classification of tweets into positive, negative and neutral sentiments. Our model is primarily a supervised one which consists of well designed features fed into an SVM classifier. In previous runs of this task, it was found that lexicons played an important role in determining the sentiment of a tweet. We use existing lexicons to extract lexicon specific features. The lexicon based features are further augmented by tweet specific fea- tures. We also improve our system by using acronym and emoticon dictionaries. The pro- posed system achieves an F1 score of 59.83 and 67.04 on the Test Data and Progress Data respectively. This placed us at the 18th posi- tion for the Test Dataset and the 16th position for the Progress Test Dataset. 1 Introduction Micro-blogging has become a very popular com- munication tool among Internet users. Millions of users share opinions on different aspects of life, ev- eryday on popular websites such as Twitter, Tum- blr and Facebook. Spurred by this growth, compa- nies and media organizations are increasingly seek- ing ways to mine these social media for informa- tion about what people think about their companies and products. Political parties may be interested to know if people support their program or not. Social organizations may need to know people’s opinion on current debates. All this information can be ob- tained from micro-blogging services, as their users post their opinions on many aspects of their life reg- ularly. Twitter contains an enormous number of text posts ∗The author is also a researcher at Microsoft (gman- ish@microsoft.com) and the rate of posts is increasing every day. Its au- dience varies from regular users to celebrities, com- pany representatives, politicians, and even coun- try presidents. Therefore, it is possible to collect text posts of users from different social and inter- est groups. However, analyzing Twitter data comes with its own bag of difficulties. Tweets are small in length, thus ambiguous. The informal style of writ- ing, a distinct usage of orthography, acronymization and a different set of elements like hashtags, user mentions demand a different approach to solve this problem. In this work we present the description of the super- vised machine learning system developed while par- ticipating in the shared task of message based sen- timent analysis in SemEval 2015 (Rosenthal et al., 2015). The system takes as input a tweet message, pre-processes it, extracts features and finally classi- fies it as either positive, negative or neutral. Tweets in the …

Content truncated to 500 words