The time-varying nature of social media sentiments in modeling stock returns

Chi San Ho, Paul Damien, Bin Gu, Prabhudev Konana

Research output: Contribution to journalArticlepeer-review

33 Scopus citations


The broad aim of this paper is to answer the following query: is the relationship between social media sentiments and stock returns time-varying? To provide a satisfactory response, a novel methodology-a symbiosis of Bayesian Dynamic Linear Models and Seemingly Unrelated Regressions -is introduced. Two sets of Dow Jones Industrial Average stock data and corresponding social media data from Yahoo! Finance stock message boards are used in a comprehensive empirical study. Some key findings are: (a) Affirmative response to the above question; (b) Models with only social media sentiments and market returns perform at least as well as models that include Fama-French and Momentum factors; (c) There are significant correlations between stocks, ranging from -0.8 to 0.6 in both data sets.

Original languageEnglish (US)
JournalDecision Support Systems
StateAccepted/In press - Jan 13 2017


  • Bayesian inference
  • Dynamic Linear Models
  • Markov chain Monte Carlo
  • Seemingly Unrelated Regressions
  • Social media sentiments

ASJC Scopus subject areas

  • Management Information Systems
  • Information Systems
  • Developmental and Educational Psychology
  • Arts and Humanities (miscellaneous)
  • Information Systems and Management


Dive into the research topics of 'The time-varying nature of social media sentiments in modeling stock returns'. Together they form a unique fingerprint.

Cite this