IOA: Improving SVM Based Sentiment Classification Through Post Processing

Proceedings of the 9th International Workshop on Semantic Evaluation (SemEval 2015), pages 545–550, Denver, Colorado, June 4-5, 2015. c⃝2015 Association for Computational Linguistics IOA: Improving SVM Based Sentiment Classification Through Post Processing Peijia Li, Weiqun Xu, Chenglong Ma, Jia Sun, Yonghong Yan The Key Laboratory of Speech Acoustics and Content Understanding Institute of Acoustics, Chinese Academy of Sciences No. 21 North 4th Ring West Road, Haidian District, 100190 Beijing, China {lipeijia,xuweiqun,machenglong,sunjia,yanyonghong}@hccl.ioa.ac.cn Abstract This paper describes our systems for expression-level and message-level sentiment analysis – two subtasks of SemEval-2015 Task 10 on sentiment analysis in Twitter. First we built two baseline systems for the two sub- tasks using SVM with a variety of features. Then we improved the systems through model iteration and probability-output weighting respectively. Our submissions are ranked the 3rd and 2nd among eleven teams on the 2015 test set and progress test set in subtask A and the 7th and 4th among 40 teams on the two test sets respectively in subtask B. 1 Introduction Recently sentiment analysis has become one of the most popular research topics in the natural language processing community, mainly due to the exponen- tial growth of social media data replete with sub- jective information. The once neglected topic has spurred immense interests from both academia and industry. Many approaches have been proposed for sentiment analysis in customer reviews, blogs and microblogs (for good reviews, see (Pang and Lee, 2008; Liu, 2012; Kiritchenko et al., 2014)). These approaches can be roughly divided into two cate- gories. One is knowledge intensive or rule-based approaches, e.g., (Taboada et al., 2011; Reckman et al., 2013). Such approaches can achieve reasonably good results when tailored for a specific domain but their maintainability and cross domain portability is usually weak. The other is data intensive or machine learning-based, which learns to analyse sentiment from data. It is currently the most predominant ap- proach, including supervised learning, deep learning etc. Sentiment analysis is often taken as a classifica- tion task. Widely used classifiers include Support Vector Machines (SVM), Maximum Entropy Mod- els (MaxEnt), and naive Bayes classifiers. Common features include word/character n-grams and senti- ment lexicons, among others. Key research issues for learning approaches include feature engineering, model selection, ensemble learning, etc. SemEval 2015 task10 (Rosenthal et al., 2015) is a sequel to the two tasks on sentiment analysis in Twitter in the past two years (Nakov et al., 2013; Rosenthal et al., 2014). They have provided freely available, annotated corpus as a common testbed and significantly promoted sentiment analysis in tweet- like short and informal texts. The same metric, i.e., the average F1 score of positive and negative classes, is used for measuring performances. But this year there are some changes. Besides the classi- cal expression-level (A) and message-level (B) sub- tasks, another three subtasks are added, i.e., subtask C – topic-based message polarity classification, sub- task D – detecting trends towards a topic, and sub- task E – determining strength of association of twit- ter terms with positive …

Content truncated to 500 words