JMUGCS · Jointly Mining User Generated Content Sources

The advent of web 2.0 empowered users to actively interact with the Web instead of passively consuming web content. Today, Web users contribute content to blogs, wiki sites, review portals, and organize themselves into online social networks where they form relationships post their thoughts and activities, and interact with each other. Individuals can now have a “presence” on the web that goes well beyond creating a home page and some documents. This kind of data is a goldmine for scientific research with an unlimited number of practical applications. In this proposed research we are interested in jointly mining user-generated content with other sources of data, in order to enhance our understanding of data, and improve the knowledge extraction process. We consider two settings: jointly mining two different sources of user-generated content, and jointly mining user-generated content with structured data. We propose problems within these two settings, focusing on ranking, and translation of user-generated attributes.