A Genetic System for Cluster Analysis for Hypertext Documents
Lando M. di Carlantonio · Seventh International Conference on Intelligent Systems Design and Applications (ISDA 2007) · 2007
Due to the increase in the number of WWW home pages, we are facing new challenges for information retrieval and indexing. Some "intelligent" techniques, including neural networks, symbolic learning, and genetic algorithms have been used to group different classes of data in an efficient way. This article describes a system for cluster analysis of hypertext documents based on genetic algorithms. The effectiveness of the system in getting groups with similar documents is evidenced by the experimental results.