Signal or Noise in Social Media Discussions: Investigating the Role of Network Cohesion
44 Pages Posted: 9 Jan 2017 Last revised: 13 Nov 2019
Date Written: November 2019
Prior studies have shown that social media discussions can be helpful in predicting price movements in financial markets. With the increasingly large amount of social media data, how to effectively distinguish value-relevant information from noise remains an important question. We study this question by investigating the role of discussion network cohesion in the relationship between social media sentiment and price changes. As network cohesion is associated with information correlation within the discussion network, we hypothesize that less cohesive social media discussion networks are better at predicting the next-day returns. We empirically test our hypothesis in the Bitcoin market using message board data collected from Bitcointalk.org. We find results consistent with our hypothesis, and our trading simulations further demonstrate how to exploit network cohesion to distinguish signal from noise in social media data and improve trading profits.
Keywords: social media analytics, network cohesion, financial technology, Bitcoin
Suggested Citation: Suggested Citation