Title: How to gauge investor behavior: A comparison of online investor sentiment measures
Authors: Simon Behrendt - Zeppelin University (Germany) [presenting]
Daniele Ballinari - University of St Gallen (Switzerland)
Abstract: Given the increasing interest in and the growing number of publicly available methods to estimate investor sentiment from social media platforms, researchers and practitioners alike are facing one important question - which is best to gauge investor sentiment? We compare the performance of daily investor sentiment measures estimated from Twitter and StockTwits short messages by publicly available dictionary and neural network based methods for a sample of 360 stocks over a seven years time period. To determine their relevance for financial applications, these investor sentiment measures are compared by (i) their effect on the cross-section of returns and (ii) their ability to forecast abnormal portfolio returns and trading volume. We provide a clear ranking of the considered online investor sentiment measures, elaborate on the reasons for the differences in performance across measures and add a note on the well-known reversal effect.