Investor sentiment from internet message postings and the predictability of stock returns

• Published in: Journal of economic behavior & organization Vol. 107; pp. 708 - 729
• Main Authors: Kim, Soon-Ho, Kim, Dongcheol
• Format: Journal Article
• Language: English
• Published: Amsterdam Elsevier B.V 01-11-2014; Elsevier Sequoia S.A
• Subjects: Artificial intelligence; Internet posting messages; Internet stocks; Investments; Investor behavior; Investor sentiment; Rates of return; Regression analysis; Return predictability; Stock prices; Studies; Text classification; Trading volume; Volatility; Internet posting messages; Return predictability; Volatility; G10; Investor sentiment; G14; Text classification; Trading volume
• ISSN: 0167-2681; 1879-1751
• DOI: 10.1016/j.jebo.2014.04.015

By using an extensive dataset of more than 32 million messages on 91 firms posted on the Yahoo! Finance message board over the period January 2005 to December 2010, we examine whether investor sentiment as expressed in posted messages has predictive power for stock returns, volatility, and trading volume. In intertemporal and cross-sectional regression analyses, we find no evidence that investor sentiment forecasts future stock returns either at the aggregate or at the individual firm level. Rather, we find evidence that investor sentiment is positively affected by prior stock price performance. We also find no significant evidence that investor sentiment from Internet postings has predictive power for volatility and trading volume. A distinctive feature of our study is the use of sentiment information explicitly revealed by retail investors as well as classified by a machine learning classification algorithm and a much longer sample period relative to prior studies.