Beyond Relevance: Adapting Exploration/Exploitation in Information Retrieval

We present a novel adaptation technique for search engines to better support information-seeking activities that include both lookup and exploratory tasks. Building on previous findings, we describe (1) a classifier that recognizes task type (lookup vs. exploratory) as a user is searching and (2) a reinforcement learning based search engine that adapts accordingly the balance of exploration/exploitation in ranking the documents. This allows supporting both task types surreptitiously without changing the familiar list-based interface. Search results include more diverse results when users are exploring and more precise results for lookup tasks. Users found more useful results in exploratory tasks when compared to a baseline system, which is specifically tuned for lookup tasks. Author Keywords Exploratory search; models of search behavior; reinforcement learning; lookup search; adaptive systems. ACM Classification Keywords H.5.m. Information Interfaces and Presentation (e.g. HCI): M...

• Type: Journal
• Year: 2016
• Where: IUI
• Authors: Kumaripaba Athukorala, Alan Medlar, Antti Oulasvirta, Giulio Jacucci, Dorota Glowacka
• Keywords: IUI 2016, Software Engineering