Affective Social Computing Laboratory
Current projects
One of our current research interests involves working on the societal need for computer-based interventions to help address the growing epidemics of behavioral issues (e.g. obesity, alcohol or drug abuse, lack of exercise, unsafe sex) that put people at-risk of getting sick. We are interested in finding new modes of delivery for evidence-based interventions for healthy lifestyle promotion, namely via engaging, supportive, and personal virtual self-help agents (personal virtual coaches) with whom people can converse anytime, anywhere, to get expert - non-judgmental - guidance.
The following article summarizes how we think that Embodied Conversational Agents (ECAs) and expressive empathic virtual characters can have a major positive impact toward helping people develop intrinsic motivation to change lifestyles (click to download): C. L. Lisetti (2012). 10 Advantages of using Avatars in Patient-centered Computer-based Interventions for Behavior Change. ACM SIGHIT Record, March 2012, Volume 2, Issue 1.
The following article summarizes how we think that Embodied Conversational Agents (ECAs) and expressive empathic virtual characters can have a major positive impact toward helping people develop intrinsic motivation to change lifestyles (click to download): C. L. Lisetti (2012). 10 Advantages of using Avatars in Patient-centered Computer-based Interventions for Behavior Change. ACM SIGHIT Record, March 2012, Volume 2, Issue 1.
|
HapFACS 1.0: Software/API for generating FACS-based facial expressions
Our HapFACS system developed with Haptek 3D characters aims at facial expression generation based on Ekman's (1992) Facial Action Coding Systems (FACS) - the current standard on facial coding of the human face - aims at enabling: 1) researchers on expressive characters to design a set of FACS-based facial expressions on the Haptek virtual character platform and to integrate their expressive avatars in their application; and 2) researchers on facial expression recognition to experiment with realistically generated expressions at the level of 49 individual Action Units (AUs). Our work is described in the following article (click on title to download): R. Amini, U. Yasavur, C. L. Lisetti (2012). HapFACS 1.0: Software/API for Generating FACS-Based Facial Expressions. In Proceedings of the ACM 3rd International Symposium on Facial Analysis and Animation (FAA'12), (Vienna, AUSTRIA, September, 2012). |
|
|
On-Demand VIrtual Counselor (ODVIC)
In this project, we design and implement the prototype of On-Demand VIrtual Counselor (ODVIC) intelligent virtual characters who can provide people access to effective behavior change interventions and help them find and cultivate motivation to change unhealthy lifestyles (e.g. excessive alcohol use, overeating). An empathic Embodied Conversational Agent (ECA) delivers the intervention. The health dialog is directed by a computational model of Motivational Interviewing, a novel effective face-to-face patient-centered counseling style which respects an individual’s pace toward behavior change. Although conducted on a small sample size, results of a preliminary user study to asses users’ acceptance of the virtual character counselor indicate that the system prototype is well accepted by 75% of users. Our work is described in the following articles (click on title to download): C. L. Lisetti, U. Yasavur, C. de Leon, R. Amini, U. Visser, R. Rishe (2012). Building On-demand Avatar-based Health Intervention for Behavior Change. In Proceedings of the 25th International FLAIRS Conference, (Marco Island, USA, May 2012). U. Yasavur, R. Amini, C. L. Lisetti (2012). User Modeling for Pervasive Alcohol Intervention Systems. In Proceedings of the Workshop on Recommendation Technologies for Lifestyle Change, In conjunction with the 6th ACM Conference on Recommender Systems (RecSys'12), (Dublin, IRELAND, September 2012). |
|
Dialog systems for behavior change
This project aims at developing dialog systems for behavior change, specifically recognizing people psycholinguistic patterns toward potential health-promoting lifestyle behavior change. We specifically investigate Adaptations of Brief Motivational Interviewing (AMI) techniques. |
