دانلود رایگان مقاله اثرات مختلف اخبار محرک و ابتکاری حجم جستجو بر قیمت سهام

Abstract

Big data benefits both Internet finance and behavioral finance research; Internet search frequency on stocks has been widely used to measure investor attention. In this study, we divide the search volume into news-driven and self-initiated by the online media coverage collected from Baidu Index. In a sample of CSI 300 stocks from 2009 to 2013, we find that self-initiated (news-driven) search volume is more likely to generate buy (sell) pressure, and media coverage can negatively moderate the impact of search volume on stock prices, suggesting that distinguishing search environment for investors can help improve the measure for investor attention.

5. Conclusion

Both enterprises and scholars have noticed the great value of big data. Baidu has already closed its service of offering SVI and MCI for most stocks (besides financial-related search terms and other search terms such as movies are still available), and regards it as confidential data. With the progress of Internet technology and the arrival of big data, Da et al. [8] successfully found a direct proxy (weekly SVI from Google Trends) to measure retail investors’ attention in a timely manner. The current related studies confirmed the impact of investor attention on the stock market, and this is the first step as information is useless without attention. The implicit assumption in existing studies is that attention measured under different situations is considered as equal. Our study extends the current studies to the second step: attention heterogeneity. In search of attention heterogeneity and its impact on stock prices, we use a dataset from China’s stock market and Baidu Index. We find a certain proportion of search volume that is news-driven and divide the search volume into news-driven and self-initiated based on the presence of news. The empirical results suggest that an increase in self-initiated search volume predicts higher stock prices in the next 2 weeks, while an increase in news-driven search volume predicts lower stock prices in the future. In other words, self-initiated (news-driven) search volume is more likely to generate buy (sell) pressure. The negative moderating effect of online media coverage indicates that the same amount of search volume is more powerful when under lower media coverage.