Call for Position Papers and Participation Workshop on Information Retrieval in Context (IRiX) ACM SIGIR Conference 2004 Sheffield, England: July 29, 2004 (http://www.sigir.org/sigir2004) Organizers: Peter Ingwersen, Royal School of LIS, Denmark Keith van Rijsbergen, University of Glasgow, Scotland Nick Belkin, Rutgers University, USA Organizing/Review Committee: Nick Belkin, Rutgers University, USA Pia Borlund, Royal School of LIS, Aalborg, Denmark Yves Chiaramella, IMAG, Grenoble, France Peter Ingwersen, Royal School of LIS, Copenhagen, Denmark Birger Larsen, Royal School of LIS, Copenhagen, Denmark Andrew MacFarlane, City University, London, UK Keith van Rijsbergen, University of Glasgow, Scotland Ian Ruthven, University of Strathclyde, Scotland Eero Sormunen, University of Tampere, Finland Amanda Spink, University of Pittsburgh, USA Pertti Vakkari, University of Tampere, Finland Motivation, themes, and goals: Motivation: There is a growing realisation that relevant information will be accessible increasingly across media and genres, across languages and across modalities. The retrieval of such information will depend on time, place, history of interaction, task in hand, and a range of other factors that are not given explicitly but are implicit in the interaction and ambient environment, namely the context. IR research is now conducted in multi-media, multi-lingual, and multi-modal environments but largely out of context. However, such contextual data can be used effectively to constrain retrieval of information thereby reducing the complexity of the retrieval process. To achieve this, context models for different modalities will need to be developed so that they can be deployed effectively to enhance retrieval performance. Thus truly context-aware and -dependent retrieval will become feasible. Context implies interactive IR and there may exist a stratification of contexts in association to IR engines and systems. For example, knowing where a user is focusing his or her attention during image retrieval can enhance the operation of relevance feedback to the system. The user's current task situation also acts as context as does his or her current information seeking situation of which IIR forms part. The underlying hypothesis (and belief) is that by taking account of context the next generation of retrieval engines dependent on models of context can be created, designed and developed delivering performance exceeding that of out-of-context engines. Themes: This workshop will explore a variety of theoretical frameworks, characteristics and research approaches to focus on an agenda of activities to be recommended for future interactive IR (IIR) research. We welcome presentation submissions connected with any aspect of the above, including the following: - Case studies, user-oriented approaches, simulations, etc. of IR in context - Contextual IR theory - modeling context, e.g. - Ontology and knowledge-based IR in context - Theoretical tools for IRiX - Evaluation and research methodologies for IRiX - Usability evaluation - Interactive IR and interface issues - Nature of relevance in contexts - Measures of performance in context and situation-sensitive IR - The test-collection challenge - Platforms and frameworks for doing research on IRiX - IR & DB Integration in context - Non-content based IR - Document structure in contextual IR - Context-sensitive information access - Algorithmic solutions - Task-based IIR - Relevance feedback & query modification issues - Media and genre-dependent applications - Cross-media, cross-language and cross-modal approaches - Personalized and collaborative information access in context Goal: The Workshop intends to outline a workable agenda for future research on IR in Context by substantiating the variation of characteristics and recommendable approaches dealing with information in context. Workshop program: - Presentations and demos sessions (accepted submissions) - Panel presentations (tailored by the Program Committee) - Discussion sessions on research approaches and questions Important dates: Submissions: May 27, 2002 Notification of acceptance: June 12, 2004 Final camera ready submissions: June 27, 2004 Workshop: July 29, 2004 How to submit a paper/demo proposal for the workshop: Please send to blar@db.dk (Dr. Birger Larsen) by email in PDF or postscript format the following: - A short bio (max 200 words) in plain ASCII - A position paper or extended abstract of less than 2000 words for one of 3 tracks: (a) Oral presentation, (b) Research in progress, (c) System demos The position paper should be formatted according to the standard SIGIR templates available at: http://www.sigir.org/sigir2004/papers.htm - and then converted to pdf or postscript. Submissions will be reviewed by the organizing and review committee and invitations to present will be sent accordingly. Accepted submissions will be included in the Working Notes to be distributed during the workshop.