Beschreibung:
We examine stock market efficiency using Twitter as proxy for the dissemination of public information. Using a sample of 8,221,848 tweets, we mine the information carried on different types of trading days. We build a set of classifiers to predict market movements based on the tweets of the previous day and validate it using an independent sample on five indices of the NYSE. Our best classifier can accurately predict 55.99% (45.51%) of bear (bull) trading days, thus pointing to semi-efficient market. By executing our approach on subperiods corresponding to financial turbulence, we show that market efficiency increases during such periods