Main Profile

At A Glance

Relevance Feedback: Getting the Most out of Your User

Google Tech TalksFebruary, 29 2008ABSTRACTRelevance feedback was one of the first interactive information retrievaltechniques to help systems learn more about users' interests. Relevancefeedback has been used in a variety of IR applications including queryexpansion, term disambiguation, user profiling, filtering andpersonalization. Initial relevance feedback techniques were explicit, inthat they required the user's active participation. Many of today'srelevance feedback techniques are implicit and based on users' informationseeking behaviors, such as the pages they choose to visit, the frequencywith which they visit pages, and the length of time pages are displayed.Although this type of information is available in great abundance, it isdifficult to interpret without understanding more about the user's searchgoals and context.In this talk, I will address the following questions: what techniques areavailable to help us learn about users' interests and preferences? Whattypes of evidence are available through a user's interactions with thesystem and with the information provided by the system? What do we need toknow to accurately interpret and use this evidence?I will address the first two questions by presenting an overview ofrelevance feedback research in information retrieval. I will address thethird question by presenting results of some of my own research thatexamined the online information seeking behaviors of users during a14-week period and the context in which these behaviors took place.Speaker: Diane KellyDiane is an assistant professor in the School of Information and Library Sciences at the University of North Carolina. Her research interests, in her own words: "I am interested in the design and evaluation of systems that support interactive information retrieval. My research explores techniques that support interactive information retrieval at the search interface, such as those used for explicit and implicit relevance feedback. My research also focuses on user modeling and personalization. Specifically, I am interested in identifying and evaluating how an online information system can learn and use the document preferences of its users through monitoring observable behaviors, such as display time and retention. I am also interested in understanding how contextual variables, such as specific task and topic, affect this relationship, and how these variables can be measured and tracked over time."
Length: 01:00:55

Contact

Questions about Relevance Feedback: Getting the Most out of Your User

Want more info about Relevance Feedback: Getting the Most out of Your User? Get free advice from education experts and Noodle community members.

  • Answer

Ask a New Question