Full Program »
File
pdf 1.1MB |
We implement a novel approach to derive investor sentiment from messages posted on social media before exploring the relation between online investor sentiment and intraday stock returns. We use an extensive dataset of messages posted on the microblogging StockTwits to construct a lexicon of words used by online investors when sharing opinions and ideas about the bullishness or the bearishness of the stock market. We demonstrate that a transparent and replicable approach significantly outperforms standard dictionary-based methods used on the literature while remaining competitive with more complex machine learning algorithms. Aggregating individual messages sentiment at half-hour intervals, we provide empirical evidences that online investor sentiment helps forecasting intraday stock index returns. After controlling for past market returns, we find that first half-hour change in investor sentiment predicts last half-hour S\&P 500 index ETF return. Examining users' self-reported investment approach, holding period and experience level, we find that the intraday sentiment effect is driven by the shift in sentiment of novice traders. Overall, our results provide direct empirical evidences of sentiment-driven noise trading at the intraday level.
Author(s):
Thomas Renault
IESEG School of Management, Université Paris 1 Panthéon-Sorbonne
France