@inproceedings{mao2015quantifying,
author = {Mao, Huina and Counts, Scott and Bollen, Johan},
title = {Quantifying the Effects of Online Bullishness on International Financial Markets},
year = {2015},
month = {January},
abstract = {Computational methods to gauge investor sentiment from large-scale online data sources using machine learning classifiers and lexicons have shown considerable promise, but suffer from measurement and classification errors. In our work we develop a simple, direct, and unambiguous indicator of online investor sentiment, which is extracted from Twitter updates and Google search queries. We examine the predictive power of this new investor Bullishness indicator on international stock markets. Our results indicate several striking regularities. First, changes in Twitter bullishness predict changes in Google bullishness, indicating that Twitter information precedes Google queries. Second, Twitter and Google bullishness are positively correlated with and lead the investor sentiment survey. Especially, the former has greater stock market predictive value than the latter. Third, we observe high Twitter bullishness predicts increases of stock returns, followed by a reversal to the fundamentals. We speculate that our results support the investor sentiment hypothesis in behavioral finance},
url = {http://approjects.co.za/?big=en-us/research/publication/quantifying-effects-online-bullishness-international-financial-markets/},
}