Paper: Chinese Sentence-Level Sentiment Classification Based on Fuzzy Sets

ACL ID C10-2036
Title Chinese Sentence-Level Sentiment Classification Based on Fuzzy Sets
Venue International Conference on Computational Linguistics
Session Poster Session
Year 2010
Authors

This paper presents a fuzzy set theory based approach to Chinese sentence-level sentiment classification. Compared with traditional topic-based text classification techniques, the fuzzy set theory provides a straightforward way to model the intrinsic fuzziness between sentiment polarity classes. To approach fuzzy sentiment classification, we first propose a fine-to-coarse strategy to estimate sentence sentiment intensity. Then, we define three fuzzy sets to represent the respective sentiment polarity classes, namely positive, negative and neutral sentiments. Based on sentence sentiment intensities, we further build membership functions to indicate the degrees of an opinionated sentence in different fuzzy sets. Finally, we determine sentence-level polarity under maximum ...