Investor sentiment extracted from internet stock message boards and IPO puzzles

High initial returns and long-run underperformance of initial public offerings (IPOs) represent puzzles in corporate finance. We investigate how investor sentiment affects these puzzles. Investor sentiment on each issuing firm's pre-IPO is extracted from Yahoo! Japan Finance message boards using text mining and a support vector machine classification. Message data on 654 Japanese IPOs from 2001 to 2010 are used to measure investor attention and sentiment. We find that high investor attention and bullish investor sentiment positively affect IPO offer prices and initial returns, leading to subsequent price declines. This suggests that excessive investor optimism can partially explain the IPO puzzles.