Automatic Social Role Recognition in Professional Meetings

This paper investigates the influence of social roles on the conversation style and linguistic usage of participants in professional meeting recordings. At first, we implement a generative model to capture the sequential nature of conversations in terms of participants, turntaking behavior. In parallel, the system also employs a probabilistic discriminative classifier on a set of high level features. The final step involves combining evidence from both generative and discriminate models. Experiments suggest that both generative and discriminative models can reach a recognition accuracy of 65% in classifying four social roles. Moreover, the recognition accuracy increases to 69% when information from both models is taken into consideration.