Predicting Stock Market Returns Based on the Content of Annual Report Narrative: A New Anomaly

This paper uses the tools of computational linguistics to analyze the qualitative part of the annual reports of UK listed companies. More specifically, the frequency of words associated with praise, concreteness and activity is measured and used to forecast future stock returns. We find that our language indicators predict subsequent price increases, even after controlling for a wide range of factors. Elevated values of the linguistic variables, however, are not symptomatic of exacerbated risk. Consequently, investors are advised to peruse the annual report narrative, as it contains valuable information that may still not have been discounted in the prices.