THESUS: Organizing Web document collections based on link semantics

2003 ◽  
Vol 12 (4) ◽  
pp. 320-332 ◽  
Author(s):  
Maria Halkidi ◽  
Benjamin Nguyen ◽  
Iraklis Varlamis ◽  
Michalis Vazirgiannis
2001 ◽  
Vol 41 (2) ◽  
pp. 253-258 ◽  
Author(s):  
Georgios V. Gkoutos ◽  
Philip R. Kenway ◽  
Henry S. Rzepa

Author(s):  
Antonio M. Rinaldi

The need to manage electronic documents is an open issue in the digital era. It becomes a challenging problem on the internet where a large amount of data needs even more efficient and effective methods and techniques for mining and representing information. In this context, document summarization, browsing processes and visualization techniques have had a great impact on several dimensions of user information perception. In this context, the use of ontologies for knowledge representation has rapidly grown in the last years in several application domains together with social-based techniques such as tag clouds. This form of visualization tool is becoming particularly useful in the interaction process between users and social applications where a huge amount of data needs to have effective and efficient interfaces. In this article, the authors propose a novel methodology based on a combination of ontologies and Tag Clouds for web document collections browsing and summarizing, they call this tool Semantic Tag Cloud.


Author(s):  
ADAM SCHENKER ◽  
MARK LAST ◽  
HORST BUNKE ◽  
ABRAHAM KANDEL

In this paper we describe a classification method that allows the use of graph-based representations of data instead of traditional vector-based representations. We compare the vector approach combined with the k-Nearest Neighbor (k-NN) algorithm to the graph-matching approach when classifying three different web document collections, using the leave-one-out approach for measuring classification accuracy. We also compare the performance of different graph distance measures as well as various document representations that utilize graphs. The results show the graph-based approach can outperform traditional vector-based methods in terms of accuracy, dimensionality and execution time.


Author(s):  
Philippe Caillou ◽  
Jonas Renault ◽  
Jean-Daniel Fekete ◽  
Anne-Catherine Letournel ◽  
Michele Sebag

Sign in / Sign up

Export Citation Format

Share Document