Material Detail

Automatic Dominance Detection In Meetings Using Support Vector Machines

Automatic Dominance Detection In Meetings Using Support Vector Machines

This video was recorded at 2nd Joint Workshop on Multimodal Interaction and Related Machine Learning Algorithms, Edinburgh 2005. 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.... Show More

Quality

  • User Rating
  • Comments
  • Learning Exercises
  • Bookmark Collections
  • Course ePortfolios
  • Accessibility Info

More about this material

Comments

Log in to participate in the discussions or sign up if you are not already a MERLOT member.