Article ID: | iaor20073848 |
Country: | United Kingdom |
Volume: | 33 |
Issue: | 1 |
Start Page Number: | 65 |
End Page Number: | 71 |
Publication Date: | Feb 2005 |
Journal: | OMEGA |
Authors: | Pesch Erwin, Baewicz Jacek, Sterna Magorzata |
Keywords: | datamining, internet |
The paper presents a new graph representation, the graph matrix, which combines the adjacency matrix with the linked lists allowing for the fastest possible access to different types of information on a graph. This is increasingly important for a high search performance, for instance, for rapidly extracting information from the link structure in a hub and authority graph of the World-Wide-Web. A very recent application for the proposed data structure arises from categorical data clustering defining proximity and similarity of data through their patterns of co-occurrence.