Humboldt-Universität zu Berlin, International Research Training Group 1792 "High Dimensional Nonstationary Time Series", Berlin
We uncover networks from news articles to study cross-sectional stock returns. By analyzing a huge dataset of more than 1 million news articles collected from the internet, we construct time-varying directed networks of the S&P500 stocks. The well-defined directed news networks are formed based on a modest assumption about firm-specific news structure, and we propose an algorithm to tackle type-I errors in identifying the stock tickers. We find strong evidence for the comovement effect between the news-linked stocks returns and reversal effect from the lead stock return on the 1-day ahead follower stock return, after controlling for many known effects. Furthermore, a series of portfolio tests reveal that the news network attention proxy, network degree, provides a robust and significant cross-sectional predictability of the monthly stock returns. Among different types of news linkages, the linkages of within-sector stocks, large size lead firms, and lead firms with lower stock liquidity are crucial for cross-sectional predictability.