Academic Research Insight: The Social Media Factor

  • Title: THE SIXTH FACTOR- A SOCIAL MEDIA FACTOR DERIVED DIRECTLY FROM MEDIA SENTIMENTS
  • Authors:        JIM LIEW AND TAMAS BUDAVARI
  • Publication: THE JOURNAL OF PORTFOLIO MANAGEMENT, SPRING 2017 (version here)

What are the research questions?

  1. Does the social media factor (created using tweet sentiments from StockTwits.com) explain the time-series variation in return for a sample of securities?
  2. Is the six factors model (the five factors Fama-French model PLUS the social media factor) better at explaining the cross-section of future returns?

What are the Academic Insights?

With the strong caveat that this study is tested on a short time frame ( January 2013-November 2015) and on a small sample ( 15 stocks), it finds that:

  1. YES- positive sentiment ( defined as the BULLISH percentage) on stocks is associated with positive returns
  2. YES- the relationship between stock twits and future returns  survives beyond the presence of traditional factors ( the Fama-French five factors model)

Why does it matter?

Financial technology (fintech) is undoubtedly changing the mechanism through which information is assembled and delivered.  It is plausible to expect that prices should incorporate all publicly available information both from traditional and non-traditional sources (such as tweets). However, would such a study pass the Harvey et al. (2016) “smell test” of robust research?

The most important chart of the paper:

The results are hypothetical results and are NOT an indicator of future results and do NOT represent returns that any investor actually attained. Indexes are unmanaged, do not reflect management or trading fees, and one cannot invest directly in an index. Additional information regarding the construction of these results is available upon request.