We present a procedure for conversational floor annotation and discuss floor types and floor switches in face-to-face meetings and the relation with addressing behavior. It seems that for understanding interactions in meetings an agent needs a layered floor model and that turn and floor changes are constrained by the activities and the roles that the agent and his conversational partners play in these activities. We present statistics about the addressee of the speaker and his role in the ongoing activity and a simple method that predicts the addressee using speaker role and floor state. The results support the expectation that information about the activity and the speaker's role will improve detection and interpretation of social signals from speaker addressee patterns in meetings.
|Workshop||2nd International Workshop on Social Signal Processing, SSPW 2010|
|Period||21/10/10 → 21/10/10|
|Other||21 October 2010|
- Conversational Analysis
- EC Grant Agreement nr.: FP7/231287