Media, sentiment and market performance in the long run
研究发现媒体悲观情绪能提前14-17个月预测负收益、24-25个月预测正收益，并提前1-20个月预测波动率，对投资者情绪指数和波动率指数有额外预测力。
This paper investigates the impact of media pessimism on financial market returns and volatility in the long run. We hypothesize that media sentiment translates into investor sentiment. Based on the underreaction and overreaction hypotheses [Barberis, N., A. Shleifer, and R. Vishny. 1998. “A Model of Investor Sentiment.” Journal of Empirical Economics 49 (3): 307–343], we suggest that media pessimism has an effect on market performance after a lag of several months. We construct a monthly media pessimism indicator by taking the ratio of the number of newspaper articles that contain predetermined negative words to the number of newspaper articles that contain predetermined positive words in the headline and in the lead paragraph. Our results indicate that media pessimism is associated with negative (positive) market returns 14–17 (24–25) months in advance and positive market volatilities 1–20 months in advance. Our results are statistically and economically significant. We find evidence for Granger causality of media pessimism on market performance. Our media pessimism indicator possesses additional predictive power for the Baker and Wurgler [2006. “Investor Sentiment and the Cross-section of Stock Returns.” Journal of Finance 61 (4): 1645–1680] investor sentiment index and the Chicago Board Options Exchange Market Volatility Index.