Vinodkumar Prabhakaran
Thu 06 Aug 2015, 15:00 - 16:30
Informatics Forum (IF-4.31/4.33)

If you have a question about this talk, please contact: Diana Dalla Costa (ddallac)

Abstract: In this talk, I will present our study on how social power relations affect the way people interact with one another and how we can use statistical machine learning techniques to detect these power relations automatically. This study is performed in the domain of organizational emails using the Enron email corpus. I will first present the problem of predicting superior-subordinate relationship between pairs of people, based solely on the language and structure of interactions within single email threads. We found many dialog behavior patterns that are salient to the direction of power. For example, managers tend to send shorter messages, and use more overt displays of power than others. I will then present the results of our investigation on how the gender of the participants impacts the manifestations of power. For example, do male managers and female managers differ in how often they use overt displays of power?


Bio: Vinodkumar Prabhakaran recently obtained a PhD in Computer Science from Columbia University under the supervision of Dr. Owen Rambow. He will be starting a postdoctoral fellowship at Stanford University with Prof. Dan Jurafsky in the fall of 2015. In his PhD thesis, he studied the language and structure of social interactions to discover patterns that help automatically infer the underlying social contexts in which those interactions occurred. His research draws from theories and models in linguistics, social sciences, and psychology, and it adopts statistical NLP and machine learning techniques. As part of his research, he has made significant contributions to core NLP problems such as semantic analysis, dialog analysis, and topic modeling. He has also worked on more applied NLP problems such as biomedical relation extraction, question answering, negation detection, and information retrieval as part of industrial internships at Siemens Corporate Research, Avaya Labs, IBM Watson, and Google. His research has been published at various top-tier NLP conferences such as ACL, NAACL, EMNLP, COLING, and IJCNLP.