Social network analysis

Abstract

Online social networking services play an increasingly important role in the private and public lives of hundreds of millions of individuals, capturing the most minute details of their whereabouts, thoughts, opinions, feelings, and activities, in real-time. Advances in social network analysis and natural language processing have enabled computational social science which leverages computational methods and large-scale data to develop models of individual and collective behavior to explain and predict a variety of economy, financial, and social phenomena. In this keynote I provide an overview of the ability of large groups of people to collectively produce information that is dynamic, complex, and adaptive. In addition to explicit information, text analysis algorithm can be used to extract indicators of social mood and sentiment from social media data. Researchers have used these techniques to gauge national happiness as well as consumer sentiment towards particular brands and products. Perhaps most tantalizing, evidence has been found that online social mood and sentiment may yield predictive information with regards to a variety of socio-economic phenomena, such as movie box office receipts, product adoption rates, elections, public health, and even stock market fluctuations. With respect to the latter, I will outline our own research on the subject of stock market prediction from large-scale Twitter and Google Trends data, and discuss recent efforts to leverage social media data to study scientific communication. © AIT Austrian Institute of Technology GmbH Vienna 2013.