Keynote by David Elsweiler

We are pleased to announce that David Elsweiler will be giving the keynote at CaRR 2014.

Abstract: Behaviour with Search and Recommender Systems: what can it tell us?

Recommender Systems and IR are technically very similar problems, but are typically treated separately and often investigated by different groups of researchers. Looking at how people behave with such systems can be one way of unifying the problem, as well as the researchers, and can also be a useful, complementary evaluation method.  When examining user behaviour, context is crucial.  By focusing on the user behaviour and the encapsulating context, we can ask questions about tools that combine search and recsys like: when do people prefer to search and when do they prefer recommendations? What does this mean for what they are trying to achieve? In this talk I will try to answer such questions with examples from leisure and health domains. Finally, looking towards the future, I will argue that the relationship between search and recommender systems and behaviour can go full circle i.e., that both have the potential to impact on user behaviour in positive ways, and will present some ideas that I together with collaborators are doing to explore this.


David Elsweiler is a lecturer and post-doctoral researcher at the University of Regensburg, Germany. Before that he was an Alexander von Humboldt Research Fellow at the University of Erlangen-Nuremberg also in Germany.  David’s research focuses on understanding information behaviour with the main aim of designing information systems that align with the way people think and behave naturally. He received his Ph.D from the University of Strathclyde, United Kingdom in 2007. David has published 50 conference papers, journal articles and book chapters on personal information management, search and recommender systems, as well as user studies investigating what users want from such systems and how they behave to achieve their aims. David has won several awards including an ACM SIGIR Outstanding Paper Award (2011) and an Emerald Outstanding Author Contribution Award for best book chapter (2011).

This year he is general co-chair for the Information Interaction in Context Conference ( and he has previously co-organised successful workshops at ACM SIGIR, BCS, ECIR, CIKM, ASIST and CSCW on topics such as Desktop Search, Evaluation of Personal Search, Searching4Fun, Personal Information Management and Living-labs Evaluation.

Keynote by Paul Bennett

We are delighted to announce that Paul Bennett will give a keynote at our workshop:

Mining and Learning from Context in Search

Abstract: Information retrieval has made significant progress in returning relevant results for a single query. However, much search activity is conducted within a much richer context of a current task focus, recent search activities as well as longer-term preferences. For example, our ability to accurately interpret the current query can be informed by knowledge of the web pages a searcher was viewing when initiating the search or recent actions of the searcher such as queries issued, results clicked, and pages viewed. We develop a framework that enables representation of a broad variety of context including the searcher’s long-term interests, recent activity, current focus, and other user characteristics. We then demonstrate how that can be used to improve the quality of search results. We describe recent progress on three key challenges in this domain: enriching information retrieval via automatically generated metadata; mining contextual signals from large scale logs; and using contextual representations in learning to improve both standard ad hoc and personalized retrieval.

Bio: Paul Bennett is a Researcher in the Context, Learning & User Experience for Search (CLUES) group at Microsoft Research where he focuses on the development, improvement, and analysis of machine learning and data mining methods as components of real-world, large-scale adaptive systems. His research has advanced techniques for ensemble methods and the combination of information sources, calibration, consensus methods for noisy supervision labels, active learning and evaluation, supervised classification (with an emphasis on hierarchical classification) and ranking with applications to information retrieval, crowdsourcing, behavioral modeling and analysis, and personalization. He completed his dissertation on combining text classifiers using reliability indicators in 2006 at Carnegie Mellon where he was advised by Profs. Jaime Carbonell and John Lafferty.

CaRR 2013

We’re happy to announce that the Workshop on Context-awareness in Retrieval and Recommendation will be returning for a third installment. This time CaRR will be organized in conjunction with the Sixth ACM International Conference on Web Search and Data Mining (WSDM ’13) in Rome in February 2013.

We’ll be updating the website shortly with detailed information on submission dates. The tentative dates for CaRR 2013 are

  • Paper submission: November 30th, 2012
  • Notifications: December 20th, 2012
  • Camera Ready: January 10th, 2013
  • Workshop: February 5th, 2013

Keynote by Anthony Jameson

We are delighted to announce that Anthony Jameson will give a keynote at our workshop:

Roles of Context in Information Retrieval and Recommendation: A Choice and Decision Making Perspective

Abstract: Systems for information retrieval and recommendation can be seen as tools that help people make good choices and decisions: about which documents to read, which products to buy, which people to contact, …. Taking this perspective, we can exploit insights from psychological research on how people make choices and decisions – in particular, on the role played by psychologically relevant contextual factors such as current goals, mood, time pressure, and distractions. In this talk, after looking at a compact overview of the diverse psychological processes involved in choosing – ranging from choices made quickly and intuitively to deliberate decisions – we will consider some questions about the roles of context in these processes: How can context influence a person’s current information need or the value that they attach to a particular item? How can context influence how such needs and evaluations are expressed or reflected in behavior (even if it doesn’t influence these things themselves)? And in the light of the answers to these questions: To what extent do people actually have needs and evaluations which exist independently of the contexts in which they are reflected in behavior? Implications for the design and study of context-aware systems for retrieval and recommendation will be discussed with audience participation.

Short Bio

Anthony Jameson is a principal researcher at DFKI, the German Research Center for Artificial Intelligence, where he heads the recently founded research unit on Choosability Engineering, which synthesizes and exploits knowledge about human choice and decision making in the design and study of (intelligent) interactive systems. Much of his research over the past three decades has addressed various aspects of user modeling and recommendation in interdisciplinary ways. He is the author of the chapter Choices and Decisions of Computer Users in the forthcoming third edition of the Human-Computer Interaction Handbook and founding coeditor-in-chief (with John Riedl) of the ACM Transactions on Interactive Intelligent Systems.