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 base-line system, which is specifically tuned for lookup tasks.

[1]  Kevin Li,et al.  Faceted metadata for image search and browsing , 2003, CHI '03.

[2]  Forbes Gibb,et al.  Uncertainty in information seeking and retrieval: A study in an academic environment , 2011, Inf. Process. Manag..

[3]  Ben Shneiderman,et al.  From Keyword Search to Exploration: How Result Visualization Aids Discovery on the Web , 2008 .

[4]  Michael R. Berthold,et al.  EVE: a framework for event detection , 2013, Evol. Syst..

[5]  Ryen W. White,et al.  Exploratory Search: Beyond the Query-Response Paradigm , 2009, Exploratory Search: Beyond the Query-Response Paradigm.

[6]  Tovi Grossman,et al.  Citeology: visualizing paper genealogy , 2012, CHI EA '12.

[7]  Mika Käki,et al.  Findex: search result categories help users when document ranking fails , 2005, CHI.

[8]  Peter Auer,et al.  Using Confidence Bounds for Exploitation-Exploration Trade-offs , 2003, J. Mach. Learn. Res..

[9]  Terry Winograd,et al.  SenseMaker: an information-exploration interface supporting the contextual evolution of a user's interests , 1997, CHI.

[10]  João Gama,et al.  A survey on concept drift adaptation , 2014, ACM Comput. Surv..

[11]  W. Cleveland.  Robust Locally Weighted Regression and Smoothing Scatterplots , 1979 .

[12]  R. Engle,et al.  Working-memory capacity, proactive interference, and divided attention: limits on long-term memory retrieval. , 2000, Journal of experimental psychology. Learning, memory, and cognition.

[13]  Ryen W. White,et al.  Personalized models of search satisfaction , 2013, CIKM.

[14]  Dorota Glowacka,et al.  Is exploratory search different? A comparison of information search behavior for exploratory and lookup tasks , 2016, J. Assoc. Inf. Sci. Technol..

[15]  Ernestina Menasalvas Ruiz,et al.  Learning recurring concepts from data streams with a context-aware ensemble , 2011, SAC.

[16]  Bernard J. Jansen,et al.  A review of web searching studies and a framework for future research , 2001 .

[17]  Albert Bifet,et al.  Sentiment Knowledge Discovery in Twitter Streaming Data , 2010, Discovery Science.

[18]  Brian Mac Namee,et al.  Handling Concept Drift in a Text Data Stream Constrained by High Labelling Cost , 2010, FLAIRS.

[19]  Ryen W. White,et al.  Struggling or exploring?: disambiguating long search sessions , 2014, WSDM.

[20]  Nicholas J. Belkin,et al.  Some(what) grand challenges for information retrieval , 2008, SIGF.

[21]  Jacek Gwizdka,et al.  Inferring user knowledge level from eye movement patterns , 2013, Inf. Process. Manag..

[22]  Dorota Glowacka,et al.  Directing exploratory search: reinforcement learning from user interactions with keywords , 2013, IUI '13.

[23]  Marti A. Hearst.  Search User Interfaces , 2009 .

[24]  Filip Radlinski,et al.  Learning diverse rankings with multi-armed bandits , 2008, ICML '08.

[25]  Albert Bifet,et al.  GNUsmail: Open Framework for On-line Email Classification , 2010, ECAI.

[26]  Ricard Gavaldà,et al.  Learning from Time-Changing Data with Adaptive Windowing , 2007, SDM.

[27]  Xin Fu,et al.  Elicitation of term relevance feedback: an investigation of term source and context , 2006, SIGIR.

[28]  Dorota Glowacka,et al.  Balancing Exploration and Exploitation: Empirical Parameterization of Exploratory Search Systems , 2015, CIKM.

[29]  Stephen E. Robertson,et al.  A probabilistic model of information retrieval: development and comparative experiments - Part 2 , 2000, Inf. Process. Manag..

[30]  Susan Wiedenbeck,et al.  PATTERNS OF INFORMATION SEEKING ON THE WEB: A QUALITATIVE STUDY OF DOMAIN EXPERTISE AND WEB EXPERTISE , 2003 .

[31]  Abdelhamid Bouchachia,et al.  Incremental learning with multi-level adaptation , 2011, Neurocomputing.

[32]  Ryen W. White,et al.  Supporting exploratory search , 2006 .

[33]  ChengXiang Zhai,et al.  Exploration-exploitation tradeoff in interactive relevance feedback , 2010, CIKM '10.

[34]  Aniket Kittur,et al.  Apolo: making sense of large network data by combining rich user interaction and machine learning , 2011, CHI.

[35]  Aiko M. Hormann,et al.  Programs for Machine Learning. Part I , 1962, Inf. Control..

[36]  Abdigani Diriye,et al.  Search interfaces for known-item and exploratory search tasks , 2012 .

[37]  Peter Pirolli,et al.  Information Foraging , 2009, Encyclopedia of Database Systems.

[38]  Dorota Glowacka,et al.  Narrow or Broad?: Estimating Subjective Specificity in Exploratory Search , 2014, CIKM.

[39]  Gary Marchionini,et al.  Exploratory search , 2006, Commun. ACM.

[40]  J. Ross Quinlan,et al.  C4.5: Programs for Machine Learning , 1992 .

[41]  Ryen W. White,et al.  Predicting short-term interests using activity-based search context , 2010, CIKM.

[42]  Eve E. Hoggan,et al.  Information-seeking behaviors of computer scientists: Challenges for electronic literature search tools , 2013, ASIST.

[43]  James Allan,et al.  Predicting searcher frustration , 2010, SIGIR.