Analysis of the relevance of sentiment data for the prediction of excess returns in a multiasset framework

Abstract

In this study, we look at the relevance of sentiment data for the prediction of excess returns in a multiasset analysis. We start by initial exploratory data analysis in order to assess the pertinence of the sentiment data. We then compare the performance of rule‐based algorithms with and without the sentiment data. The data considered are provided by RavenPack. Finally, we explore the economic relevance of the forecast model in a long‐only and long‐short context. Inclusion of sentiment data leads to encouraging results.