Social Information Processing
Google Tech Talks
June 20, 2007
The label 'social media' has been attached to a quickly growing number of Web sites whose content is primarily user-driven. Examples of these sites include: blogs --- personal online journals that allow users to share their thoughts and receive feedback on them; Wikipedia --- collectively written and edited online encyclopedia; Flickr, Del.icio.us and Digg --- Web sites that allow users to share, discuss and rank photos, Web pages and news stories respectively. In the process of using social media sites, users are adding metadata in the form of tags, ratings and social networks.
While each of the metadata types above offers a rich source of evidence on its own, the connections between them create a treasure trove of rich interlinked data that will revolutionize information processing. The collective knowledge and opinions generated independently by many users will lead to new solutions to hard information processing problems. In this talk I will describe application of social metadata to four information processing problems: recommendation, collaborative evaluation of documents, information personalization and information discovery.
Kristina Lerman is an Assistant research professor at the Computer Science Department at USC and a Project Leader at the USC Information Sciences Institute. She received a PhD in physics from UC Santa Barbara in 1995. Her research interests include semantic modeling of information source, mathematical analysis of multi-agent systems, and lately, social web and social information processing.