ARTICLE Salamin_IEEETRANSACTIONSONMULTIMEDIA_2009/IDIAP Automatic Role Recognition in Multiparty Recordings: Using Social Affiliation Networks for Feature Extraction Salamin, Hugues Favre, Sarah Vinciarelli, Alessandro EXTERNAL http://publications.idiap.ch/attachments/papers/2009/Salamin_IEEETRANSACTIONSONMULTIMEDIA_2009.pdf PUBLIC IEEE Transactions on Multimedia 11 7 1373-1380 2009 November 2009 Automatic analysis of social interactions attracts increasing attention in the multimedia community. This paper considers one of the most important aspects of the problem, namely the roles played by individuals interacting in different settings. In particular, this work proposes an automatic approach for the recognition of roles in both production environment contexts (e.g., news and talk-shows) and spontaneous situations (e.g., meetings). The experiments are performed over roughly 90 hours of material (one of the largest databases used for role recognition in the literature) and show that the recognition effectiveness depends on how much the roles influence the behavior of people. Furthermore, this work proposes the first approach for modeling mutual dependences between roles and assesses its effect on role recognition performance.