Correlating financial time series with micro-blogging activity

• DOI: 10.1145/2124295.2124358
• Publication Date: 2012-02-14T13:21:44Z
• Authors: Eduardo J. Ruiz; Vagelis Hristidis; Carlos Castillo; Aristides Gionis; Alejandro Jaimes
• Keywords: Stock (firearms); Microblogging

We study the problem of correlating micro-blogging activity with stock-market events, defined as changes in price and traded volume stocks. Specifically, we collect messages related to a number companies, search for correlations between events those companies features extracted from messages. The extract can be categorized two groups. Features first group measure overall platform, such posts, re-posts, so on. second properties an induced interaction graph, instance, connected components, statistics on degree distribution, other graph-based properties.