Predicting continuous conflict perception with Bayesian Gaussian processes

Kim, S., Valente, F., Filippone, M. and Vinciarelli, A. (2014) Predicting continuous conflict perception with Bayesian Gaussian processes. IEEE Transactions on Affective Computing, 5(2), pp. 187-200. (doi: 10.1109/TAFFC.2014.2324564)

Abstract

Conflict is one of the most important phenomena of social life, but it is still largely neglected by the computing community. This work proposes an approach that detects common conversational social signals (loudness, overlapping speech, etc.) and predicts the conflict level perceived by human observers in continuous, non-categorical terms. The proposed regression approach is fully Bayesian and it adopts Automatic Relevance Determination to identify the social signals that influence most the outcome of the prediction. The experiments are performed over the SSPNet Conflict Corpus, a publicly available collection of 1430 clips extracted from televised political debates (roughly 12 hours of material for 138 subjects in total). The results show that it is possible to achieve a correlation close to 0.8 between actual and predicted conflict perception.

• Item Type: Articles
• Status: Published
• Refereed: Yes
• Glasgow Author(s) Enlighten ID: Vinciarelli, Professor Alessandro and Filippone, Dr Maurizio
• Authors: Kim, S., Valente, F., Filippone, M., and Vinciarelli, A.
• Subjects: B Philosophy. Psychology. Religion > BF Psychology; Q Science > QA Mathematics > QA75 Electronic computers. Computer science
• College/School: College of Science and Engineering > School of Computing Science
• Research Group: Social Signal Processing
• Journal Name: IEEE Transactions on Affective Computing
• Publisher: IEEE
• ISSN: 1949-3045
• ISSN (Online): 1949-3045
• Copyright Holders: Copyright © 2014 IEEE
• First Published: First published in IEEE Transactions on Affective Computing 5(2):187-200
• Publisher Policy: Reproduced in accordance with the copyright policy of the publisher

Related URLs

• Author

Project Code	Award No	Project Name	Principal Investigator	Funder's Name	Funder Ref	Lead Dept
54388	1	SSPNet - Social Signal Processing Network.	Alessandro Vinciarelli	European Commission (EC)	UNSPECIFIED	COM - COMPUTING SCIENCE
		Interactive Multimodal Information Management	Alessandro Vinciarelli	Swiss National Science Foundation	UNSPECIFIED	Computing Science