On the Use of Explanations as Mediating Device for Relevance Feedback
In this paper we examine the role of explanations as a means of facilitating the use of relevance feedback in information retrieval systems. We do this with particular reference to previous experimental work. This demonstrates that explanations can increase the user’s willingness to interact more fully with the system. We outline the general conclusions from this experimental work and discuss the implications for interactive IR systems that incorporate relevance feedback.
Unable to display preview. Download preview PDF.
- 1.Belkin, N. J. On the nature and function of explanation in intelligent information retrieval. Proceedings of the 11th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval. Grenoble. (1988) 135–145Google Scholar
- 2.Cawsey, A. Explanation and interaction: the computer generation of explanatory dialogues. MIT Press. (1992)Google Scholar
- 3.Dennis, S., McArthur, R. and Bruza, P. Searching the WWW made easy? The Cognitive Load imposed by Query Refinement Mechanisms. Proceedings of the Third Australian Document Computing Symposium. (1998)Google Scholar
- 4.Fowkes, H. and Beaulieu, M. Interactive searching behaviour: Okapi experiment for TREC-8. IRSG 2000 Colloquium on IR Research. electronic Workshops in Computing. Cambridge. (2000)Google Scholar
- 5.Harman, D. Relevance feedback and other query modification techniques. Information Retrieval: Data Structures & Algorithms. Englewood Cliffs: Prentice Hall. (W.B. Frakes and R. Baeza-Yates ed). Chapter 11. ( 1992) 241–263Google Scholar
- 7.Ruthven, I. Abduction, explanation and relevance feedback. PhD Thesis. University of Glasgow. (2001)Google Scholar
- 8.Ruthven, I., Lalmas, M. and van Rijsbergen, C. J. Incorporating User Search Behaviour into Relevance Feedback. 2002 (Submitted for Publication).Google Scholar
- 9.Ruthven, I., Tombros, A. and Jose, J. A study on the use of summaries and summary-based query expansion for a question-answering task. 23rd BCS European Annual Colloquium on Information Retrieval Research (ECIR 2001). Darmstadt. (2001)Google Scholar