On the fractal nature of mutual relevance sequences in the Internet news message flows

Abstract

In the task of information retrieval the term relevance is taken to mean formal conformity of a document given by the retrieval system to user's information query. As a rule, the documents found by the retrieval system should be submitted to the user in a certain order. Therefore, a retrieval perceived as a selection of documents formally solving the user's query, should be supplemented with a certain procedure of processing a relevant set. It would be natural to introduce a quantitative measure of document conformity to query, i.e. the relevance measure. Since no single rule exists for the determination of the relevance measure, we shall consider two of them which are the simplest in our opinion. The proposed approach does not suppose any restrictions and can be applied to other relevance measures.