论文信息 - NILC_USP: A Hybrid System for Sentiment Analysis in Twitter Messages

NILC_USP: A Hybrid System for Sentiment Analysis in Twitter Messages

This paper describes the NILC USP system that participated in SemEval-2013 Task 2: Sentiment Analysis in Twitter. Our system adopts a hybrid classification process that uses three classification approaches: rulebased, lexicon-based and machine learning approaches. We suggest a pipeline architecture that extracts the best characteristics from each classifier. Our system achieved an Fscore of 56.31% in the Twitter message-level subtask.

Thiago Pardo | Pedro Balage Filho | T. Pardo | P. B. Filho

[1] Arvid Kappas,et al. Sentiment in short strength detection informal text , 2010, J. Assoc. Inf. Sci. Technol..

[2] Rizal Setya Perdana. What is Twitter , 2013 .

[3] Walter Daelemans,et al. Pattern for Python , 2012, J. Mach. Learn. Res..

[4] Maite Taboada,et al. Lexicon-Based Methods for Sentiment Analysis , 2011, CL.

[5] Eric Brill,et al. Reducing the human overhead in text categorization , 2006, KDD '06.

[6] Owen Rambow,et al. Sentiment Analysis of Twitter Data , 2011 .

[7] Mike Thelwall,et al. Sentiment in short strength detection informal text , 2010 .

[8] Hosung Park,et al. What is Twitter, a social network or a news media? , 2010, WWW '10.

[9] Preslav Nakov,et al. SemEval-2013 Task 2: Sentiment Analysis in Twitter , 2013, *SEMEVAL.

[10] Timothy W. Finin,et al. Why we twitter: understanding microblogging usage and communities , 2007, WebKDD/SNA-KDD '07.

[11] Ari Rappoport,et al. Enhanced Sentiment Learning Using Twitter Hashtags and Smileys , 2010, COLING.

[12] Rudy Prabowo,et al. Sentiment analysis: A combined approach , 2009, J. Informetrics.

[13] Bo Pang,et al. Thumbs up? Sentiment Classification using Machine Learning Techniques , 2002, EMNLP.

[14] David A. Shamma,et al. Characterizing debate performance via aggregated twitter sentiment , 2010, CHI.