ABSTRACT
We analyze methods for selecting topics in news articles to explain stock returns. We find, through empirical and theoretical results, that supervised Latent Dirichlet Allocation (sLDA) implemented through Gibbs sampling in a stochastic EM algorithm will often overfit returns to the detriment of the topic model. We obtain better out-of-sample performance through a random search of plain LDA models. A branching procedure that reinforces effective topic assignments often performs best. We test these methods on an archive of over 90,000 news articles about S&P 500 firms.
- David M Blei, Andrew Y Ng, and Michael I Jordan. 2003. Latent dirichlet allocation. JMLR 3, Jan (2003), 993--1022.Google ScholarDigital Library
- Jordan Boyd-Graber and Philip Resnik. 2010. Holistic sentiment analysis across languages: Multilingual supervised latent dirichlet allocation. In EMNLP. 45--55.Google Scholar
- John Campbell. 1991. A variance decomposition for stock returns. The Economic Journal (1991), 157--179.Google Scholar
- Thomas L Griffiths and Mark Steyvers. 2004. Finding scientific topics. PNAS 101, suppl 1 (2004), 5228--5235.Google ScholarCross Ref
- Michael Hughes, Gabriel Hope, Leah Weiner, Thomas McCoy, Roy Perlis, Erik Sudderth, and Finale Doshi-Velez. 2018. Semi-supervised prediction-constrained topic models. In AISTAT. 1067--1076.Google Scholar
- Tim Loughran and Bill McDonald. 2011. When is a liability not a liability? Textual analysis, dictionaries, and 10-Ks. Journal of Finance 66, 35--65.Google Scholar
- Jon D Mcauliffe and David M Blei. 2008. Supervised topic models. In NeurIPS. 121--128.Google Scholar
- Thien Hai Nguyen and Kiyoaki Shirai. 2015. Topic modeling based sentiment analysis on social media for stock market prediction. In ACL. 1354--1364.Google Scholar
- Richard Roll. 1988. R2. Journal of Finance 43 (3), 541--566.Google Scholar
- P. Tetlock, M. Saar-Tsechansky, and S. Macskassy. 2008. More Than Words: Quantifying Language to Measure Firms' Fundamentals. Journal of Finance 63, 3 (2008), 1437--1467.Google ScholarCross Ref
- Paul C Tetlock. 2014. Information transmission in finance. Annu. Rev. Financ. Econ. 6, 1, 365--384.Google Scholar
- Cheng Zhang and Hedvig Kjellström. 2014. How to supervise topic models. In ECCV. Springer, 500--515.Google Scholar
Index Terms
- Choosing news topics to explain stock market returns
Recommendations
Ex-Day Returns of Stock Distributions: An Anchoring Explanation
We offer a new anchoring explanation for the ex-day abnormal returns of stock distributions, including stock dividend distributions, splits, and reverse splits. We propose that investors tend to anchor on cum-day prices in valuating ex-distribution stocks,...
The Impact of the COVID-19 Pandemic on the Stock Market Returns: Evidence from the Chinese Stock Market
ICCMB '23: Proceedings of the 2023 6th International Conference on Computers in Management and BusinessThis study investigates the association between the Chinese stock market returns and the COVID-19 pandemic. The empirical results reveal that the COVID-19 pandemic negatively impacts stock market returns. We report our findings first by investigating ...
Investor Sentiment and Stock Returns, Evidence from Chinese Securities Market
BCGIN '13: Proceedings of the 2013 International Conference on Business Computing and Global InformatizationBased on the method of Baker&Wurgler, we create a comprehensive investor sentiment indicator using the principal component analysis and aim to examine the relationships between investor sentiment and market return, stock portfolio returns and industry ...
Comments