Berlin 2012 – scientific programme

Parts | Days | Selection | Search | Updates | Downloads | Help

SOE: Fachverband Physik sozio-ökonomischer Systeme

SOE 13: Communication and Language

SOE 13.3: Talk

Wednesday, March 28, 2012, 14:30–14:45, H 0110

Sentiment Classification in Social Media - an exemplar study in the micro-blogging platform Twitter — •René Pfitzner, Antonios Garas, and Frank Schweitzer — Chair of Systems Design, ETH Zurich, Switzerland

Social Mediae are changing the way people communicate and stay in touch. One particular case, the micro-blogging platform Twitter, has gained much scientific attention in the last one or two years. This attention is justified by its inherent openness that allows public accessibility to user profiles, and to user contributions expressed through short texts (called "tweets"), leaving researchers with valuable datasets. Here we study the "tweeting" behavior of users, by distinguishing between the pure act of "tweeting" as information creation mechanism, and the practice of "retweeting" as information distribution mechanism. Especially, by determining the emotional value of a tweet using SentiStrength, an automated sentiment classifier for short and informal text, we consider the influence of the emotional value of a tweet on its chances of diffusion in the network.