Title :
Extracting Sentiment of Fund Investors from Small Talk on the Web
Author :
Wang, Bo ; Liu, XianFeng ; Pu, Zhong
Author_Institution :
Economic Manage. Sch., SouthWest Pet. Univ., Chengdu, China
Abstract :
Reviews on Web can help small investors make decision in selecting funds. The size of fund reviews is smaller than other products, which proposes a challenge to extract sentiment by using statistic methods. We develop a methodology to deal with this problem by using association rule to select seed words and introducing new outside resources to improve the traditional PMI performance. The result shows that this methodology is effective.
Keywords :
Internet; data mining; investment; statistics; Web reviews; association rule; fund investors; fund reviews; seed words selection; sentiment extraction; statistic methods; Association rules; Classification algorithms; Feature extraction; Finance; Semantics; Stock markets; PMI; data mining; lexicon; outside resource; sentiment extraction;
Conference_Titel :
Computational and Information Sciences (ICCIS), 2010 International Conference on
Conference_Location :
Chengdu
Print_ISBN :
978-1-4244-8814-8
Electronic_ISBN :
978-0-7695-4270-6
DOI :
10.1109/ICCIS.2010.150