Generating Domain-Specific Clues Using News Corpus for Sentiment Classification

Proceedings of the International AAAI Conference on Web and Social Media, 4

Volume

Vol. 4 No. 1 (2010): Fourth International AAAI Conference on Weblogs and Social Media

Poster Papers

This paper addresses the problem of automatically generating domain-specific sentiment clues. The main idea is to bootstrap from a small seed set and generate new clues by using dependencies and collocation information between sentiment clues and sentence-level topics that would be a primary subject of sentiment expression (e.g., event, company, and person). The experiments show that the aggregated clues are effective for sentiment classification.

10.1609/icwsm.v4i1.14073