Title :
Transfer cross entropy for fast sociometric inference in longitudinal collections of multi-party conversation
Author :
Laskowski, Kornel
Author_Institution :
Carnegie Mellon Univ., Pittsburgh, PA, USA
Abstract :
A means is proposed of extracting participant-pair interaction measures from a binary representation of behavior in multi-party conversation, by leveraging an extension of transfer entropy. The technique allows for the inexpensive construction of sociomatrices, requiring only a minimum of detection technology. It is expected that the method will tractably enable the application of social network analysis to conversational behavior mined from very large collections of unannotated audio.
Keywords :
entropy; inference mechanisms; social aspects of automation; binary representation; conversational behavior; detection technology; longitudinal collection; multiparty conversation; participant pair interaction measures; social network analysis; sociomatrices; sociometric inference; transfer cross entropy; unannotated audio; Entropy; Equations; History; Mathematical model; Production; Social network services; Speech; N-gram models; Turn-taking; cross entropy; influence; social network analysis; transfer entropy;
Conference_Titel :
Acoustics, Speech and Signal Processing (ICASSP), 2012 IEEE International Conference on
Conference_Location :
Kyoto
Print_ISBN :
978-1-4673-0045-2
Electronic_ISBN :
1520-6149
DOI :
10.1109/ICASSP.2012.6288347
