Towards an intelligent possibilistic web information retrieval using multiagent system

The purpose of this paper is to make a scientific contribution to web information retrieval (IR).

A multiagent system for web IR is proposed based on new technologies: Hierarchical Small‐Worlds (HSW) and Possibilistic Networks (PN). This system is based on a possibilistic qualitative approach which extends the quantitative one.

The paper finds that the relevance of the order of documents changes while passing from a profile to another. Even if the selected terms tend to select the relevant document, these terms are not the most frequent of the document. This criterion shows the asset of the qualitative approach of the SARIPOD system in the selection of relevant documents. The insertion of the factors of preference between query terms in the calculations of the possibility and the necessity consists in increasing the scores of possibilistic relevance of the documents containing these terms with an aim of penalizing the scores of relevance of the documents not containing them. The penalization and the increase in the scores are proportional to the capacity of the terms to discriminate between the documents of the collection.

It is planned to extend the tests of the SARIPOD system to other grammatical categories, like refining the approach for the substantives by considering for example, the verbal occurrences in names definitions, etc. Also, it is planned to carry out finer measurements of the performances of SARIPOD system by extending the tests with other types of web documents.

The system can be useful to help research students find their relevant scientific papers. It must be located in the document server of any research laboratory.

The paper presents SARIPOD, a new qualitative possibilistic model for web IR using multiagent system.