Predicting the Future With Social Media - arXiv.pdfVIP

Predicting the Future With Social Media Sitaram Asur Bernardo A. Huberman Social Computing Lab Social Computing Lab HP Labs HP Labs Palo Alto, California Palo Alto, California Email: sitaram.asur@ Email: bernardo.huberman@ 0 1 Abstract—In recent years, social media has become ubiquitous This paper reports on such a study. Specifically we consider 0 and important for social networking and content sharing. And the task of predicting box-office revenues for movies using 2 yet, the content that is generated from these websites remains the chatter from Twitter, one of the fastest growing social largely untapped. In this paper, we demonstrate how social media 1 r content can be used to predict real-world outcomes. In particular, networks in the Internet. Twitter , a micro-blogging network, a we use the chatter from T to forecast box-office has experienced a burst of popularity in recent months leading M revenues for movies. We show that a simple model built from to a huge user-base, consisting of several tens of millions of 9 the rate at which tweets are created about particular topics can users who actively participate in the creation and propagation 2 outperform market-based predictors. We further demonstrate of content. how sentiments extracted from Twitter can be further utilized to ] improve the forecasting power of social media.