Exploiting multi-evidence from multiple user's interests to personalizing information retrieval

• Published in: 2007 Second International Conference on Digital Information Management Vol. 1; pp. 7 - 12
• Main Authors: Tamine-Lechani, L., Boughanem, M., Zemirli, N.
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.10.2007
• Subjects: Bayesian methods; Clustering algorithms; Computer Science; Context modeling; Data mining; Decision making; Feedback; Information Retrieval; Multitasking; Query processing; Search engines; Query processing; Bayesian methods; Feedback; Decision making; Clustering algorithms; Search engines; Multitasking; Information retrieval; Data mining; Context modeling
• ISBN: 142441475X; 9781424414758
• DOI: 10.1109/ICDIM.2007.4444192

The goal of personalization in information retrieval is to tailor the search engine results to the specific goals, preferences and general interests of the users. We propose a novel model that considers the user's interests as sources of evidence in order to tune the accuracy of documents returned in response to the user query. The model's fundation comes from influence diagrams which are extension of Bayesian graphs, dedicated to decision-making problems. Hence, query evaluation is carried out as an inference process that aims to computing an aggregated utility of a document by considering its relevance to the query but also the corresponding utility with regard to the user's topics of interest. Experimental results using enhanced TREC collections indicate that our personalized retrieval model is effective.