Call for Paper:
IP&M Special Topic Issue on Adaptive Information Retrieval

Deadline: 30 September 2007

Call for Participation:
First International Workshop on Adaptive Information Retrieval (AIR 2006)

Date: 14 October 2006

Aim and objectives

The aim of the proposed research is the development of techniques to promote effective Web searching. This specific proposal is for the creation of search models that adapt to the information needs of the searcher. The proposed models use implicit methods to unobtrusively monitor searcher interaction, make inferences about what constitutes relevant material, create new queries and choose appropriate retrieval strategies. Traditionally, to receive such support searchers must use relevance feedback systems and make a series of explicit assessments of what information is relevant. Such systems are unpopular since assessments are difficult to make, searchers must provide this feedback and the benefits are not always apparent. In our promising earlier research, we investigated the personalisation of the search results through the use of implicit feedback models. It was demonstrated that our techniques provide effective aids to interactive searching.

However, our recent user studies have highlighted some inadequacies; that is, searchers still wished to retain control over some of the actions of the systems created, suggesting an incompleteness in the implicit techniques used. In this project we make use of these results and investigate the development of robust adaptive search models based on implicit feedback. We will establish the factors that can act as implicit feedback, study the role of context in using these factors and develop structured presentation techniques. The creation of structured information spaces can enhance the quality of the interaction that these methods use to make their decisions. This interaction, as well as appropriate affective and contextual aspects will be used to build robust adaptive search models. Effective adaptive search models will alleviate many of the problems faced by users of the web search systems, and in particular, that of novice searchers.

Related project: Personalisation of Web Searches through Ostension & Summarisation



Joho, H. and Jose, J. M. (2007) "Effectiveness of Additional Representations for the Search Result Presentation on the Web". Information Processing & Management, to appear.

Psarras, I. and Jose, J. M. (2007) "Evaluating A Personal Information Assistant." In: Proceedings of the 8th Recherche d'Information Assistée par Ordinateur Conference (RIAO 2007), to appear, Pittsburgh, PA.

Masegosa, A. R., Joho, H., and Jose, J. M. (2007) "Evaluating query-independent object features for relevancy prediction". In: Amati, G., et al. (Eds.) Advances in Information Retrieval, 29th European Conference on Information Retrieval, 283-294, Rome, Italy. Lecture Notes in Computer Science, 4425, Springer.

Joho, H., Urban, J., Villa, R., Jose, J. M., and Van Rijsbergen, C. J. (2006) "First International Workshop on Adaptive Information Retrieval: Abstract Booklet", University of Glasgow, Glasgow, UK.

Joho, H. and Jose, J. M. (2006), "Slicing and dicing the information space using local contexts". In: Ruthven, I., et al. (Eds.) Proceedings of the First Symposium on Information Interaction in Context (IIiX), 111-126, Copenhagen, Denmark.

Joho, H. and Jose, J. M. (2006), "A Comparative Study of the Effectiveness of Search Result Presentation on the Web". In: Lalmas, M., et al. (Eds.) Advances in Information Retrieval, 28th European Conference on Information Retrieval, 302-313, London, UK. Lecture Notes in Computer Science, 3936, Springer.

Psarras, I. and Jose, J. M. (2006) "A system for adaptive information retrieval." In: Proceedings of the International Conference on Adaptive Hypermedia and Adaptive Web-Based Systems (AH 2006), 313-317, Dublin, Ireland, Springer.