Automatic Dominance Detection In Meetings Using Support Vector Machines

Posted in Science on August 17, 2008


Automatic Dominance Detection In Meetings Using Support Vector Machines

We show that, using a Support Vector Machine classifier, it is possible to determine with a 75% success rate who dominated a particular meeting on the basis of a few basic features. We discuss the corpus we have used, the way we had people judge dominance and the details of the classifier and features that were used.

Author: Rutger Rienks, Human Media Interaction

Watch Video

Tags: Science, Lectures, Computer Science, Machine Learning, VideoLectures.Net, Kernel Methods