CIS Seminar - From Everyday Applications to Recommendations: Unifying Relevance feedback for Multi-application User Modeling
3:00 PM, Monday February 15 2016
235 Weir Hall
From Everyday Applications to Recommendations: Unifying Relevance feedback for Multi-application User Modeling
Abstract: Accurate models of user interest are valuable in personalizing the presentation of the often large quantity of information relevant to a query or other form of information requests. A user often interacts with multiple applications while working on a task. User models can be developed individually at each of the individual applications, but there is no easy way to come up with a more complete user model based on the distributed activity of the user. In this talk, I will introduce a novel unification framework for relevance feedback in adaptive information access; practically these models provide context for user interactions with everyday applications for user interest modeling
Specifically, I will formally define the personalized information delivery and discuss the unique properties of heterogeneous data sources that make this problem challenging. By analyzing the two most important types of relevance feedback types, implicit and explicit, I will introduce the unified framework by collectively using heterogeneous information interactions in multiple everyday applications. To tackle the cold-start problem in personalization, I will show how we can take advantage of the many existing interactions combining various implicit and explicit relevance feedback indicators in a multi-application environment. I will also present a conceptual framework expanding the use of human eye movements as a source of implicit relevance feedback for user interest modeling.
Bio: Sampath Jayarathna is a PhD candidate and a teaching fellow in the Department of Computer Science and Engineering at Texas A&M University. Sampath Obtained an MS in Computer Science at Texas State University, San Marcos, Texas. His current research interests include development of human-computer information retrieval (HCIR) and machine learning techniques for effective and efficient adaptive information access. His previous research experiences include eye tracking, human oculomotor system, and biometrics.