Paper: Automatic Detection of Opinion Bearing Words and Sentences

ACL ID I05-2011
Title Automatic Detection of Opinion Bearing Words and Sentences
Venue International Joint Conference on Natural Language Processing
Session poster-demo-tutorial
Year 2005
Authors

We describe a sentence-level opinion detection system. We first define what an opinion means in our research and introduce an effective method for ob- taining opinion-bearing and non- opinion-bearing words. Then we de- scribe recognizing opinion-bearing sen- tences using these words We test the system on 3 different test sets: MPQA data, an internal corpus, and the TREC- 2003 Novelty track data. We show that our automatic method for obtaining opinion-bearing words can be used ef- fectively to identify opinion-bearing sentences.