SeNTU: Sentiment Analysis of Tweets by Combining a Rule-based Classifier with Supervised Learning

Proceedings of the 9th International Workshop on Semantic Evaluation (SemEval 2015), pages 647–651, Denver, Colorado, June 4-5, 2015. c⃝2015 Association for Computational Linguistics SeNTU: Sentiment Analysis of Tweets by Combining a Rule-based Classifier with Supervised Learning Prerna Chikersal, Soujanya Poria, and Erik Cambria School of Computer Engineering Nanyang Technological University Singapore - 639798 {prerna1,sporia,cambria}@ntu.edu.sg Abstract We describe a Twitter sentiment analysis sys- tem developed by combining a rule-based classifier with supervised learning. We sub- mitted our results for the message-level sub- task in SemEval 2015 Task 10, and achieved a F1-score of 57.06%. The rule-based classi- fier is based on rules that are dependent on the occurrences of emoticons and opinion words in tweets. Whereas, the Support Vector Ma- chine (SVM) is trained on semantic, depen- dency, and sentiment lexicon based features. The tweets are classified as positive, negative or unknown by the rule-based classifier, and as positive, negative or neutral by the SVM. The results we obtained show that rules can help refine the SVM’s predictions. 1 Introduction Our opinions and the opinions of others play a very important role in our decision-making process and even influence our behaviour. In recent times, an increasing number of people have taken to ex- pressing their opinions on a wide variety of topics on microblogging websites such as Twitter. Be- ing able to analyse this data and extract opinions about a number of topics, can help us make informed choices and predictions regarding those topics. Due to this, sentiment analysis of tweets is gaining im- portance across a number of domains such as e- commerce (Wang and Cardie, 2014), politics (Tu- masjan et al., 2010; Johnson et al., 2012; Wang et 1We average the positive and negative F-measures to get the F-score, which is the evaluation metric for this task. al., 2012), health and psychology (Cambria et al., 2010; Harman, ; Harman, ), multimodality (Poria et al., 2015), crowd validation (Cambria et al., 2010), and even intelligence and surveillance (Jansen et al., 2009). SemEval 2015 Task 10 (Rosenthal et al., 2015) is an international shared-task competition that aims to promote research in sentiment analysis of tweets by providing annotated tweets for training, devel- opment and testing. We created a sentiment anal- ysis system to participate in the message-level task of this competition. The objective of the system is to label the sentiment of each tweet as “positive”, “negative” or “neutral”. In this paper, we describe our sentiment analysis system, which is a combined classifier created by in- tegrating a rule-based classification layer with a sup- port vector machine. 2 System Description Our Sentiment Analysis System consists of two clas- sifiers – (i) Rule-based and (ii) Supervised, inte- grated together. This section describes both these classifiers and how we combine them. During pre-processing, all the @<username> references are changes to @USER and all the URLs are changed to http://URL.com. Then, we use the CMU Twitter Tokeniser and POS Tagger (Gim- pel et al., 2011) to tokenise the tweets and give a parts-of-speech tag …

Content truncated to 500 words