Beverly Park Woolf de l’University of Massachusetts, Department of Computer Science donnera une conférence le 27 novembre de 15h à 17h à la Salle des boiseries (J-2810) Pavillon Judith-Jasmin, Université du Québec à Montréal 405, rue Sainte-Catherine Est, Montréal Métro Berri-UQAM
Abstract : This presentation describes how to recognize students’ emotion while they solve mathematics problems. We use sensors in intelligent tutors to detect students’ affective states and then embed emotional support in the tutor. The tutor dynamically collected data streams of physiological activity and students’ self-reports of emotions. Evidence indicates that fluctuating student emotions are related to larger, longer-term affective variables such as self-concept in mathematics. Students produced self-reports of their emotions and models were created to automatically infer these emotions from physiological data from the sensors. Summaries of student physiological activity helped to predict more than 80% of the variance of students’ emotional states.
We also evaluated the use of animated emotional embodied pedagogical agents and their impact on student motivation and achievement within the intelligent tutor. We integrated controlled exploration of agents’ communicative factors (facial expression, empathy, and mirroring postures) as they impact human learning, interaction and relationship development. Empirical studies show that students in the learning companions group increased their math value, self-concept and mastery orientation. Students’ self-reports of emotions while using the learning companions showed higher levels of interest and reduced boredom after 15 minutes of use of the tutor. This research also provides evidence that by modifying the “context” of the tutoring system we may well be able to optimize students’ emotion reports and in turn improve math attitudes.
Biographie : Beverly Park Woolf, Ph.D., is a Research Professor at the University of Massachusetts. Her team develops and deploys 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 (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.