Expertise finders are an important class of collaborative recommendation systems, but they suffer from a general problem: Current expertise finders, both commercial and research, cannot infer expertise levels very well. Traditionally, expertise finders have relied on the standard information similarity measures (such as term vector comparisons). However, in general, knowing level of expertise for a potential information source is very important. The classical example is medical: If you are sick, you want to find a doctor with expertise, not merely someone interested in the topic.

QuME is a prototype middleware system that contains a number of mechanisms to facilitate expertise finding, expertise exchange, and social interaction for online communities and organizations. QuME includes novel mechanisms to infer expertise levels, making a larger range of social interaction possible.  More>

Online discussions such as a large-scale community brainstorming often end up with an unorganized bramble of ideas and topics that are difficult to reuse. A process of distillation is needed to boil down a large information space into information that is concise and organized. Arkose is a system-augmented approach to the problem - a set of tools with which human editors can collaboratively distill a large amount of informal information. More>