quicker to react to news when the market is going down than when it is going up. There
is something to be said about the behavioral aspects of such a scenario. Anxiety is the
predominant sentiment in bear markets, whereas in bull markets complacency tends to
be more common amongst investors. Similar results are documented in Hou, Peng, and
Xiong (2009).
9.5 Conclusion
As the preceding results demonstrate, news sentiment can be used to obtain long-term
positive excess stock returns. Our brief event study illustrates a method for picking
stocks that emerge from a period of media pessimism with good forward 1-year excess
return potential. There is, however, much room for refinement in the methodology. For
example, if the minimum time period over which reversals occur were extended from one
month to one year, perhaps the optimal net news sentiment measurement period would
decrease from 17 months to only a few months, and the forward returns might improve.
Maybe instead of focusing on relevance scores, what should be used to supplement the
MCQ rankings is DJNA data related to earnings announcements ornovelty scores.^5
Another idea from Hafez (2009) is to control for the seasonality of news, although such
an approach is more germane to shorter net news sentiment measurement periods. The
possibilities are endless. On the other hand, the plethora of available variables suggest
the very real danger of data-fitting. More is needed than the bare correlation of variables
to be convinced of the presence of an anomaly. Sentiment reversals as defined here seem
to be supported not only by good performance, but a firm, intuitive hypothesis with
evidence of monotonicity in the relationship between the primary variable (net news
sentiment) and forward returns.
Future work on sentiment reversals might concentrate on developing a more market-
neutral strategy. The Monte Carlo simulations from the previous section show that the
excess returns are not uniformly distributed through time. Moreover, as is the case with
other reversal-style anomalies such as the momentum reversals first documented by
deBondt and Thaler (1985), the long side might be hedged with a relevant short side.
Of course, such a strategy would only be applicable to funds that have the ability to
short-sell. It could be that the mirror image of sentiment reversals—viz., companies
descending from an extended period of positive net news sentiment—are good short
candidates. If negative-to-positive reversals create more opportunities while the market
is going up, positive-to-negative reversals could create more opportunities while the
market is going down. The latter scenario, clearly, is an ideal time to be shorting stocks.
One might reasonably expect such a combined strategy to distribute the expected
outperformance of sentiment reversals equally over different market environments.
9.6 Acknowledgments
The author would like to thank all those who had a hand in the progress of this
work, particularly Kevin Crosbie, Peter Dickson, Alan Beimfohr, John Prichard,
Chad Neault, Peter Hafez, and David Hirshleifer.
Sentiment reversals as buy signals 243(^5) Each story is ranked according to how many preceding stories have been published about the same event.