DocumentCode :
2038138
Title :
Using the factor model to analyze Internet BBS messages and stock returns
Author :
Suwa, Hirohiko ; Umehara, Eiichi ; Ohta, Toshizumi
Author_Institution :
Grad. Sch. of Inf. Syst., Univ. of Erectro-Commun., Tokyo, Japan
fYear :
2011
fDate :
13-18 Sept. 2011
Firstpage :
2546
Lastpage :
2551
Abstract :
Whether the number and content of messages on a stock bulletin board system (BBS) relates to the stocks return has been investigated. Also verified was whether Fama and French´s three-factors approve a portfolio on the basis of the number or contents of messages on the Tokyo Stock Exchange (TSE). It was found that the three-factor model may not approve portfolios because abnormal returns were found in portfolios with the highest number of bullish postings and the highest number of bearish postings as well as the highest number of postings and the fewest number of postings. Next, the three-factor model was added to two factors: the difference in the return of a portfolio with the highest number of messages and with the fewest, and the difference in the return with the most bullish and with the most bearish. The result suggests that the contents of messages on a stock BBS may relate to a return.
Keywords :
Internet; financial data processing; information services; stock markets; Internet BBS messages; Tokyo Stock Exchange; bearish postings; bullish postings; portfolio; stock bulletin board system; stock returns; three-factor model; Analytical models; Companies; Correlation; Portfolios; Semantics; Stock markets; Support vector machine classification; Internet stock BBS; Natural language processing; Three-factor model;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
SICE Annual Conference (SICE), 2011 Proceedings of
Conference_Location :
Tokyo
ISSN :
pending
Print_ISBN :
978-1-4577-0714-8
Type :
conf
Filename :
6060408
Link To Document :
بازگشت