News Beta: Factoring Sentiment Risk into Quant Models

Abstract

The stock market is affected by sentiment. The question, however, is how to quantify this effect on asset prices. By using a news-based proxy for sentiment, this article intends to address the issue empirically by exploring the pricing implications of a stock’s exposure to market sentiment. The authors explore a concept termed news beta—the sensitivity of stock returns to changes in market sentiment as reported by the media. After controlling for traditional factors, news beta is found to have strong return predictability over 6- and 12-month horizons. The evidence from this research suggests that news sentiment data are still an untapped source of alpha in financial markets.