Distinguished Lecturer Series

Bridging Computer Science and Behavioral Science: Research Examples

Joseph A. Konstan

Distinguished McKnight Professor of Computer Science and Engineering, University of Minnesota

Friday November 6, 2009
10:30 am - SENSQ 5317

Hosted by Liz Marai

Abstract

As computers and the Internet become tools and "places" for social interaction, computer scientists and behavioral scientists can work together to explore the social and behavioral aspects of this new environment. In this talk, I will discuss two projects: one that is exploring how to induce people to participate in on-line communities (based on theories of collective action), and another that is exploring the design of online question-answering communities. I will also briefly discuss collaborative research on assessing and reducing HIV risk online.

On-line communities have great potential to rebuild the social capital that has been lost as individuals turn away from structured community events, but experience so far has been discouraging. The vast majority of on-line communities fail--they cease to serve their original goals, whether discussion or content-creation. At the same time, some specific on-line communities have succeeded spectacularly. In this part of the talk, I review the research of CommunityLab, a collaboration that brings together psychology, economics, and computer science to better understand, leverage, and design for user motivation to contribution to on-line communities.

Question-answering sites have emerged as a powerful phenomenon online. These sites serve multiple purposes, from providing a venue for "water-cooler" conversations to providing advice in challenging situations to generating high-quality content worthy of archival. In this part of the talk I review two studies of such sites -- one to explore their nature and one to demonstrate the power of machine learning to help improve their usage and design.

Biography of Speaker

Joseph A. Konstan is Distinguished McKnight Professor of Computer Science and Engineering at the University of Minnesota. His research addresses a variety of human-computer interaction and social computing issues, including personalization (particularly through recommender systems), eliciting on-line participation, and designing computer systems to improve public health. He is probably best known for his work in collaborative filtering recommenders (the GroupLens project), and for his work in online HIV prevention.

Dr. Konstan received his Ph.D. from the University of California, Berkeley in 1993. He is a Fellow of the ACM and past-President of ACM SIGCHI, the 4500-member Special Interest Group on Human-Computer Interaction. He is a member of the ACM Council, and has served as chair ACM's Special Interest Group Governing Board, and on ACM's Executive Committee. Dr. Konstan is an active consultant who has worked for more than 15 companies on issues related to human-computer interaction, personalization, and general software issues. He has traveled and lectured extensively, giving over 250 invited talks in more than 25 countries worldwide.

This Computer Science Distinguished Lecture is supported by the Google Pittsburgh.