Houlihan, Patrick, Diffusion of Price Information Through Message Volume and Sentiment (October 8, 2014). Available for download at SSRN: http://ssrn.com/abstract=2527968

“Several market data parameters have been validated to be correlated with asset price changes. In addition, many have been used as independent variables in a variety of models to help explain the direction of future asset price changes. Recently, it’s been shown that sentiment extracted from social media is correlated with future asset prices. Through a series of rigorous simulations using textual based data between July 2009 and September 2012, this research shows that message volume does help explain the diffusion of price information. We highlight several similarities between previous research that showed both positive and negative message sentiment diffuses over a period of days. Suggesting statistics derived from both message volume and message sentiment can be used as parameters in previously developed models.”