Paper: Language-Specific Sentiment Analysis in Morphologically Rich Languages

ACL ID C10-2057
Title Language-Specific Sentiment Analysis in Morphologically Rich Languages
Venue International Conference on Computational Linguistics
Session Poster Session
Year 2010
Authors

In this paper, we propose language- specific methods of sentiment analysis in morphologically rich languages. In con- trast of previous works confined to statis- tical methods, we make use of various linguistic features effectively. In particu- lar, we make chunk structures by using the dependence relations of morpheme sequences to restrain semantic scope of influence of opinionated terms. In con- clusion, our linguistic structural methods using chunking improve the results of sentiment analysis in Korean news cor- pus. This approach will aid sentiment analysis of other morphologically rich languages like Japanese and Turkish.