Internet has become the main channel of information on investment for individual investors. “market trend” is a major consideration for individual investors to investment market. Here to try to design the opinion mining system of stock, the system uses model-based method of tendentious analysis of stock analysts, to identify and extract the predictable view of statement classification and tendentious analysis of the final stock analysts. The experiment results show that the use of the approach makes the opinion mining system’s precision rate arrive at 91.7%.
2 Dave K, Lawrence S, Pennock DM. Mining the Peanut Gallery: Opinion Extraction and Semantic Classification of Product Reviews. Proc. of the 12th International World Wide Web Conference(WWW2003). Budapest, Hungary, 2003.
3 Yi J, Niblack W. Sentiment Mining in WebFountain. Proc. of the ICDE205, the 21st International Conference on Data Engineering. IEEE Computer Society. Tokyo, Japan, 2005.
4 Wilson T, Hoffmann P, Somasundaran S, Patwardhan et al. Opinion Finder: A system for subjectivity analysis. Demonstration Description in Conference on Empirical Methods in Natural Language Processing. Vancouver, 2005.
5 Liu B, et al. Opinion observer: analyzing and comparing opinions on the web. Proc. of WWW’OS, the14th International Conference on WWW. Chiba, Japan, 2005. 342- 351.
6 Jin W, Ho H, Srihari R. OpinionMiner: a novel machine learning system for web opinion mining and extraction. Proc. of KDD. 2009. 1195-1204.
12 Liu X, Mo Q, Zhang Z. Research on opinion classification of internet reviews. Journal of Beijing Technology and Bussiness University (Natural Science Edition), 2008, 26(3):61-65.
13 Tumey PD. Thumbs Up or Thumbs Down? Semantic Orientation Applied to Unsupervised Classification of Reviews. Association for Computational Linguistics 40th Anniversary Meeting(ACL), Philadelphia, 2002. 417-424.
14 Schapire RE, Singer Y. BoosTexter: A boosting-based system for text categorization. Machine Learning, 2000,39(2/3):135-168.
15 Jiang L, Yu M, Zhou M, Liu X, Zhao T. Target-dependent twitter sentiment classification. ACL. 2011.
16 Liu B. Web Data Mining-Exploring Hyperlinks, Contents, and Usage Data (2nd ed.). Berlin Heidelberg: Springer,2008.
17 Akkaya Cem, Conrad A, Wiebe J, Mihalcea R. Amazon Mechanical Turk for subjectivity word sense disambigua-码 tion. Proc. of the NAACL HLT 2010 Workshop on Creating Speech and Language Data with Amazon’s Mechanical Turk. Los Angeles, CA. 2010. 195-203.