 |
|
|
|
|
|
|
|
|
|
|
|
|
 |
|
|||||||||||
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
|
|
 |
 |
|
||||||||||
 |
|
|||||||||||
 |
|
|||||||||||
 |
 |
|
||||||||||
| Seminar Schedule (Seminar Organizer: Prof. Ziv Bar-Joseph) | |
Machine Learning Lunchtime Chats
|
Spring 2008 Seminar
Date: May 5, 2008 Time: 4:30 PM - 5:30 PM (Refreshments at 4:15) Location: 1305 Newell-Simon Hall Speaker: Lada Adamic Assistant Professor, University of Michigan Title: Expertise Sharing Dynamics in Online Forums Abstract: Web-based communities have become an important place for people to seek and share expertise. In this talk, we explore three such communities, from the technical Java Forum, to the truly diverse Yahoo! Answers, to the fee-based TackCN site in China. We first test a set of network-based ranking algorithms on the large social network of the technically oriented Java Forum, in order to identify users with high expertise. We then use simulations to identify a small number of simple rules governing the question-answer dynamic in the network. These simple rules not only replicate the structural characteristics and algorithm performance on the empirically observed Java Forum, but also allow us to evaluate how other algorithms may perform in communities with different characteristics. We then apply our analysis to the much more diverse set of question answer forums found on Yahoo! Answers, and observe different behavior for technical and non-technical categories. Finally, we analyze the competitive dynamics and effects of monetary rewards for the TaskCN website. We believe our approach to identifying expertise will be fruitful for practical algorithm design and implementation in online expertise-sharing communities. The preprints for these 3 studies can be found at http://www-personal.umich.edu/~ladamic Speaker Bio: Lada A. Adamic is an assistant professor in the School of Information and the Center for the Study of Complex Systems at the University of Michigan. Her research interests center on information dynamics in networks: how information diffuses, how it can be found, and how it influences the evolution of a network's structure. She worked previously in Hewlett-Packard's Information Dynamics Lab. Her projects have included indentifying expertise in online question answer forums, studying the dynamics of viral marketing, and characterizing the structure in blogs and other online communities.