[cs-talks] Upcoming Seminar: Bev Woolf Talk on Thursday May 21 at 2:00 PM

Greenwald, Faith fgreen1 at bu.edu
Mon May 18 11:02:20 EDT 2015

Computer Vision for Teaching and Learning
Beverly Park Woolf
College of Computer Science, University of Massachusetts, Amherst, MA.
bev at cs.umass.edu<mailto:bev at cs.umass.edu>
Thursday, May 21, 2015
2:00pm in MCS 148

This talk explores the possibility of integrating computer vision techniques with online tutors to improve teaching and learning. Emotion is vital to learning and using technology to recognize students’ emotion while learning online has led to powerful performance results.
We have used sensors (conductance bracelet, pressure mouse, posture analysis seat and camera) to detect students' emotion.  Computational tutors dynamically collected data streams of students’ physiological activity and self-reports of emotions. Summaries of student physiological activity helped to predict more than 80% of the variance of students’ emotional states. Empirical studies show that students increase their math value, self-concept and mastery orientation once they receive support triggered by their detected emotion. Evidence indicates that fluctuating student emotions are also related to larger, longer-term affective variables such as self-concept.

We also used animated pedagogical agents to impact student motivation and achievement. We integrated controlled exploration of embodied agents’ communicative factors (facial expression, empathy, and mirroring postures) as they address human learning, interaction and relationship development. Students’ self-reports of emotions while using the learning companions showed increased levels of interest and confidence and reduced levels of boredom and frustration. This research also provides evidence that by modifying the “context” of tutoring systems, e.g., by personalizing instruction and by supporting emotion, tutors can optimize students’ emotion, attitude and learning.

We will explore the possibility of detecting student emotion and grit (e.g., perseverance, frustration, anxiety) by using modern computer vision work (e.g., detect body movement, hand gestures, nods, eyebrows and grins).  Based on detecting student emotion, tutors can use interventions to address negative emotion and provide improved learning.

Beverly Park Woolf, Ph.D. is a Research Professor at the University of Massachusetts who develops intelligent tutors that model student affective and cognitive characteristics and combine cognitive analysis of learning with artificial intelligence, network technology and multimedia. These systems represent the knowledge taught, recognize which skills students have learned, use sensors and machine learning to model student affect, and adjust problems to help individual students. Tutors have been deployed in education and industry, in a variety of disciplines (e.g., chemistry, psychology, physics, geology, art history, mathematics and economics) and one is used by more than 100,000 students per semester across 100 colleges. Some of these tutors enable students to pass state standard exam at a higher rate (92%) as compared with students not using the tutor (76%).  Dr. Woolf published the book Building Intelligent Interactive Tutors along with over 200 articles; she has delivered keynote addresses, panels and tutorials in more than 20 foreign countries and is a fellow of the American Association of Artificial Intelligence.

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://cs-mailman.bu.edu/pipermail/cs-talks/attachments/20150518/f0ae16b6/attachment.html>

More information about the cs-talks mailing list