University of Cambridge > Talks.cam > Rainbow Group Seminars > Detecting engagement and positive emotions from facial expressions

Detecting engagement and positive emotions from facial expressions

Add to your list(s) Download to your calendar using vCal

If you have a question about this talk, please contact Henrik Lieng.

Engagement is often associated with better learning and higher productivity, but it is also linked with having positive experiences. A system that can detect and support engaged states would also be contributing to the users’ well-being. Psychologists have developed methods for measuring different forms of engagement, but they require time consuming manual coding and have not yet exploited new affective computing techniques for its automation. In this paper we explore how the webcam, and the more recent Kinect depth camera can be used to collect and interpret observational and self-reported data. The study introduces computer vision techniques to make inferences about engagement and emotional states, while students (N=23) engage in a structured writing activity (draft-feedback-review) similar to those used in schools and universities. Average accuracy was 47% and 33% over the base-line while detecting valence and arousal respectively. The result also shows a significant agreement between positive emotions and the user’s engagement.

This talk is part of the Rainbow Group Seminars series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.

 

© 2006-2022 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity