DFKI-LT - Fine-grained Opinion Topic and Polarity Identification

Xiwen Cheng, Feiyu Xu
Fine-grained Opinion Topic and Polarity Identification
2 Proceedings of the Poster Session of the Sixth International Conference on Language Resources and Evaluation, Marrakech, Morocco, ELRA, 5/2008
This paper presents OMINE, an opinion mining system which aims to identify concepts such as products and their attributes, and analyze their corresponding polarities. Our work pioneers at linking extracted topic terms with domain-specific concepts. Compared with previous work, taking advantage of ontological techniques, OMINE achieves 10% higher recall with the same level precision on the topic extraction task. In addition, making use of opinion patterns for sentiment analysis, OMINE improves the performance of the backup system (NGram) around 6% for positive reviews and 8% for negative ones.
Files: BibTeX, OMINE_LREC_2008.pdf