News Co-Occurrence, Attention Spillover, and Return Predictability
53 Pages Posted: 7 Mar 2017 Last revised: 8 Dec 2018
Date Written: November 18, 2018
We examine the effect of investor attention spillover on stock return predictability. Using a novel measure, the News Network Triggered Attention index (NNTA), we find that NNTA negatively predicts market returns with a monthly in(out)-of-sample R-square of 5.97% (5.80%). In the cross-section, a long-short portfolio based on news co-occurrence generates a significant monthly alpha of 68 basis points. The results are robust to the inclusion of alternative attention proxies, sentiment measures, other news- and information-based predictors, across recession and expansion periods. We further validate the attention spillover effect by showing that news co-mentioning leads to greater increases in Google and Bloomberg search volumes than unconditional news coverage. Our findings suggest that attention spillover in a news-based network can lead to significant stock market overvaluations, and especially when arbitrage is limited.
Keywords: Investors attention; Network; Return predictability; Short-sales constraint; Media coverage; News tones; Heterogeneous belief.
JEL Classification: G11, G12, G41
Suggested Citation: Suggested Citation