Unraveling the relationship between social moods and the stock market: Evidence from the United Kingdom

This study elucidates plausible relationships between various social moods-dimension and the stock market. To study this phenomenon, we consider a twitter-based data consisting of various moods-dimensions of people residing in the United Kingdom and FTSE 100 index data from January 1, 2010, to October 31, 2014. The findings report that social moods-dimension significantly impacts the market return at the aggregate level. The prediction accuracy measured by the artificial neural network is comparably higher than that of other models, such as support vector machine, discriminant analysis, and decision tree. We also observe that a specific moods-dimension named happy significantly improves the prediction of the index return. While there is no causality between aggregate social moods and the index return, we find bi-directional causality between happy mood-dimension and the market return. However, the intensity of causality from the index return to happy moods is profound. The novelty of our research lies in methodological augmentation and its congruence compared with previous empirical studies. (C) 2020 Elsevier B.V. All rights reserved.