Cristian Danescu-Niculescu-Mizil presents "Language and Social Dynamics in Online Communities"

Cristian Danescu-Niculescu-Mizil
Title: "Language and Social Dynamics in Online Communities"   Cristian Danescu-Niculescu-Mizil ABSTRACT            More and more of life is now manifested online, and many of the digital traces that are left by human activity are in natural-language format. In this talk I will show how exploiting these resources under a computational framework can bring a new understanding of online social dynamics;  I will be discussing two of my efforts in this direction. The first project explores the relation between users and their community, as revealed by patterns of linguistic change.  I will show that users follow a determined life-cycle with respect to their susceptibility to adopt new community norms, and how this insight can be harnessed to predict how long a user will stay active in the community. The second project proposes a computational framework for identifying and characterizing politeness, a central force shaping our communication behavior.  I will show how this framework can be used to study the social aspects of politeness, revealing new interactions with social status and community membership. This talk includes joint work with Dan Jurafsky, Jure Leskovec, Christopher Potts, Moritz Sudhof and Robert West.   BIOGRAPHICAL NOTE Cristian Danescu-Niculescu-Mizil is a faculty member of the Max Planck Institute SWS.  His research aims at developing computational frameworks that can lead to a better understanding of human social behavior, by unlocking the unprecedented potential of the large amounts of natural language data generated online.  His work tackles problems related to conversational behavior, opinion mining, computational pragmatics and computational advertising.  He is the recipient of several awards, including the WWW 2013 Best Paper Award and a Yahoo Key Scientific Challenges award, and his work has been featured in popular-media outlets such as the New Scientist, NBC's The Today Show, NPR and the New York Times. Cristian received his PhD in computer science from Cornell University and was a postdoctoral researcher in the computer science and linguistics departments at Stanford University.  Earlier, he earned a master's degree from Jacobs University Bremen and an undergraduate degree from the University of Bucharest.