Microblog Sentiment Analysis Method Based on Spectral Clustering

다국어 초록 (Multilingual Abstract)

This study evaluates the viewpoints of user focus incidents using microblog sentiment analysis, which hasbeen actively researched in academia. Most existing works have adopted traditional supervised machinelearning methods to analyze emotions in microblogs; however, these approaches may not be suitable inChinese due to linguistic differences. This paper proposes a new microblog sentiment analysis method thatmines associated microblog emotions based on a popular microblog through user-building combined withspectral clustering to analyze microblog content. Experimental results for a public microblog benchmarkcorpus show that the proposed method can improve identification accuracy and save manually labeled timecompared to existing methods.

참고문헌 (Reference)

1 K. Nigam, "Using maximum entropy for text classification" 61-67, 1999

2 A. Go, "Twitter sentiment analysis" Stanford University 2009

3 N. F. Da Silva, "Tweet sentiment analysis with classifier ensembles" 66 : 170-179, 2014

4 B. Pang, "Thumbs up?: sentiment classification using machine learning techniques" 79-86, 2002

5 L. Jiang, "Target-dependent twitter sentiment classification" 151-160, 2011

6 X. Dong, "Set-Similarity joins based semi-supervised sentiment analysis" 176-183, 2012

7 P. Yin, "Sentiment classification of Chinese online reviews: analysing and improving supervised machine learning" 7 (7): 381-398, 2012

8 L. Pang, "Sentiment classification method of Chinese micro-blog based on emotional knowledge" 38 (38): 2012

9 J. Xu, "Sentiment classification for Chinese news using machine learning methods" 21 (21): 95-100, 2007

10 Y. Zhang, "Sentiment analysis on microblogging by integrating text and image features" 52-63, 2015

11 A. Balahur, "Sentiment analysis in the news" 2216-2220, 2010

12 W. Medhat, "Sentiment analysis algorithms and applications: a survey" 5 (5): 1093-1113, 2014

13 W. Che, "Sentence compression for aspect-based sentiment analysis" 23 (23): 2111-2124, 2015

14 L. Barbosa, "Robust sentiment detection on twitter from biased and noisy data" 36-44, 2010

15 W. Jin, "OpinionMiner: a novel machine learning system for web opinion mining and extraction" 1195-1204, 2009

16 F. Jiang, "Microblog sentiment analysis with emoticon space model" 76-87, 2014

17 M. Taboada, "Lexicon-based methods for sentiment analysis" 37 (37): 267-307, 2011

18 Q. Liu, "Emotional tendency identification for micro-blog topics based on multiple characteristics" 280-288, 2012

19 K. L. Liu, "Emoticon smoothed language models for twitter sentiment analysis" 2012

20 G. Paltoglou, "A study of information retrieval weighting schemes for sentiment analysis" 1386-1395, 2010