Scalability and evaluation of contextual immune model for web mining

Abstract

In this chapter we focus on some problems concerning application of an immune-based algorithm to extraction and visualization of cluster structure. Particularly a hierarchical, topic-sensitive approach is proposed; it appears to be a robust solution to the problem of scalability of document map generation process (both in terms of time and space complexity). This approach relies upon extraction of a hierarchy of concepts, i.e. almost homogenous groups of documents described by unique sets of terms. To represent the content of each context a modified version the aiNet [9] algorithm is employed; it was chosen because of its natural ability to represent internal patterns existing in a training set. Careful evaluation of the effectiveness of the novel text clustering procedure is presented in section reporting experiments. © 2008 Springer-Verlag Berlin Heidelberg.