Oren Tsur: "Separated by a Common Language? A unified Framework Bridging the Gap Between Language and Networks"

Speaker: SEAS Postdoc Fellow Oren Tsur

Title: Separated by a Common Language? A Unified Framework Bridging the Gap Between Language and Networks

Abstract:

Network science mainly deals with questions about the observed and potential structure of networks. Language processing, on the other hand, typically deals with content rather than the medium and the social setting of the discourse. In my talk, I will present a unified framework that bridges the gap between the two disciplines. The framework combines topic models, sentiment analysis, regression models and network analysis. I will present results from the political domain showing how we can detect patterns of coordinated campaigns for agenda setting, framing and political spin, based on automatic analysis of large collection of public statements made by members of the US Congress. If time (and questions) permit I’ll conclude with some initial results derived from automatic construction of political networks of cooperation and influence.  

Biography:

Oren Tsur is a postdoctoral fellow at Harvard University (SEAS & IQSS) jointly with Lazer's lab at Northeastern University. He earned his PhD. in Computer Science from the Hebrew University and his research combines Natural Language Processing and Network Science. Oren received the 2014 NSF fellowship for research of Political Networks. Him and his colleagues were recognized by by Time Magazine as one of the 50 Best Inventions of 2010 for their work on sarcasm detection. Here is pop sci talk [HEB].

For more information, Oren's homepage is available here.