Attention Conditions Stock Market Reaction to News Sentiment

Instead try to understand the interaction effects between sentiment and various forms of media or investor attention. To understand how investors react to sentiment, we conduct a double sort analysis - ranking on sentiment in one dimension and on media coverage, sentiment momentum, return volatility, and price momentum in the other.

We find that conditioning news sentiment impact with attention yields higher returns.

Specifically:

• Highly volatile stocks have a very strong reaction to negative news while low volatility stocks have the strongest reaction to positive sentiment.

• Companies with negative sentiment momentum continue to underperform while those with positive sentiment momentum outperform.

• Low news flow companies outperform high news flow companies, particularly when news sentiment is negative

• Companies with extreme price momentum react strongest to negative news. Companies with moderate price momentum react most to positive news

Introduction

The emergence of news analytics has been valuable to both academics and financial practitioners in understanding the impact of news and public information on asset pricing. By now, research has led to a set of stylized facts that go beyond describing news flow characteristics. For instance, Chan [Mar, 2001] found that negative news leads to stronger price reactions than positive news - a result further supported by Cahan et.al. [May, 2009]. In the paper "Stock Price Reaction to News and No-News: Drift and Reversal after Headlines" [Mar, 2009], Chan found that negative news tends to be reflected more slowly in stock prices than positive news. In Hafez and Xie [May, 2012], we found that positive and negative events on average decay over a two and five day horizon, respectively. Several studies have also shown that price reactions to news are not only stronger for small cap than for large cap stocks, but that news based signals also decay more slowly as one moves down the size scale.

Even though the body of research continues to grow, there is still a lot to learn about how investors react to news and sentiment over time. Do investors react differently during bull or bear markets? Or when investing on different sectors or according to various company characteristics? The objective of this paper is to move beyond the simple notion of “buy on positive and sell on negative sentiment” and instead try to understand the interaction effects between sentiment and various forms of media or investor attention. To understand how investors react to sentiment, we conduct a double sort analysis - ranking on sentiment in one dimension and on various forms of attention in the other including media coverage, sentiment momentum, return volatility, and price momentum.

In the following section, we provide a brief description of our test stock universe and the data used in the study. In Section 3, we present a new methodology to calculate the company sentiment indicator tested here. In Section 4, we consider the value add of including sentiment decay as part of our indicator methodology. In Section 5, we look at the interactions effects between sentiment and attention; and evaluate its effects on various industries in Section 6. Finally, in Section 7 we present our conclusions.