UIR-PKU: Twitter-OpinMiner System for Sentiment Analysis in Twitter at SemEval 2015

Proceedings of the 9th International Workshop on Semantic Evaluation (SemEval 2015), pages 664–668, Denver, Colorado, June 4-5, 2015. c⃝2015 Association for Computational Linguistics UIR-PKU: Twitter-OpinMiner System for Sentiment Analysis in Twitter at SemEval 2015 Xu Han2,4, Binyang Li1, Jing Ma2, Yuxiao Zhang3, Gaoyan Ou3, Tengjiao Wang3, Kam-fai Wong2,4,5 1School of Information and Technology, University of Information Relations, Beijing 2Dept. of Sys. Engineering&Engineering Management, The Chinese University of Hong Kong 3School of Information Science, Peking University, Beijing 4Shenzhen Research Institute, The Chinese University of Hong Kong 5MoE Key Laboratory of High Confidence Software Technologies, China {xhan, jma, kfwong}@cuhk.edu.hk; byli@uir.cn; {yxzhang, gyou, tjwang}@pku.edu.cn Abstract Microblogs are considered as We-Media infor- mation with many real-time opinions. This paper presents a Twitter-OpinMiner system for Twitter sentiment analysis evaluation at SemEval 2015. Our approach stems from two different angles: topic detection for discovering the sentiment distri- bution on different topics and sentiment analysis based on a variety of features. Moreover, we also implemented intra-sentence discourse relations for polarity identification. We divided the discourse re- lations into 4 predefined categories, including con- tinuation, contrast, condition, and cause. These relations could facilitate us to eliminate polarity ambiguities in compound sentences where both positive and negative sentiments are appearing. Based on the SemEval 2014 and SemEval 2015 Twitter sentiment analysis task datasets, the exper- imental results show that the performance of Twit- ter-OpinMiner could effectively recognize opinionated messages and identify the polarities. 1 Introduction This year comes the third edition of SemEval Twit- ter sentiment analysis task consisting of new genres, including topic-based polarity classification, trends detection towards a topic, and the sentimental strength of association of terms (Nakov et al., 2013). Corresponding author We only participated in the subtask of message sentiment analysis and built up a system, named Twitter-OpinMiner for the task. Twitter- OpinMiner stems from two different angles: LDA- based topic detection for discovering the opinion- ated features of trending tweets’ topics and senti- ment analysis based on a variety of features.  Topic detection Recent studies show that people often search Twitter to find temporally relevant information (Teevan et al., 2011), such as emergent events, trending topics. In fact, similar opinions were likely to express on the same topic/event in Twitter. For example, there are 20 tweets expressing similar opinions on “Blood moon” in SemEval 2015 da- taset. Therefore, it can facilitate us to discover the sentiment distribution on different topics.  Sentiment analysis Unlike traditional news content, tweets are spe- cialists in short texts with long compound sen- tences, and a number of irregular expressions, including emoticon, hashtag, and special punctua- tions. In order to better support tweets analysis, we extract features from following aspects: textual content, irregular expression, discourse relations, and word embedding. Then we introduce above features into a SVM classifier for sentiment analy- sis. This paper is organized as follows. Section 2 de- scribes the framework of our system. Section 3 in- troduces the details of our feature extraction. We 664 Figure 1. System architecture. present the evaluation results in …

Content truncated to 500 words