Hierarchical Interest Graph from Tweets

TitleHierarchical Interest Graph from Tweets
Publication TypeConference Proceedings
Year of Publication2014
AuthorsPavan Kapanipathi, Prateek Jain, Chitra Venkataramani, Amit Sheth
EditorKyuseok Shim, Torsten Suel
Conference Name3rd International World Wide Web Conference
Conference LocationSeoul, South Korea
KeywordsHierarchical Interest Graph, personalization, Social Semantic Web, twitter, User Profiles, Wikipedia

Industry and researchers have identified numerous ways to mone- tize microblogs for personalization and recommendation. A com- mon challenge across these different works is the identification of user interests. Although techniques have been developed to ad- dress this challenge, a flexible approach that spans multiple lev- els of granularity in user interests has not been forthcoming. In this work, we focus on exploiting hierarchical semantics of con- cepts to infer richer user interests expressed as a Hierarchical In- terest Graph . To create such graphs, we utilize users’ tweets to first ground potential user interests to structured background knowledge such as Wikipedia Category Graph. We then adapt spreading acti- vation theory to assign user interest score to each category in the hierarchy. The Hierarchical Interest Graph not only comprises of users’ explicitly mentioned interests determined from Twitter, but also their implicit interest categories inferred from the background knowledge source.

Related Files: