@inproceedings{36db4805cf1f497ca46f7a9b7eec8bb2,
title = "Classification of web documents using a graph model",
abstract = "In this paper we describe work relating to classification of web documents using a graph-based model instead of the traditional vector-based model for document representation. We compare the classification accuracy of the vector model approach using the k- Nearest Neighbor (k-NN) algorithm to a novel approach which allows the use of graphs for document representation in the k-NN algorithm. The proposed method is evaluated on three different web document collections using the leave-one-out approach for measuring classification accuracy. The results show that the graph-based k-NN approach can outperform traditional vector-based k-NN methods in terms of both accuracy and execution time.",
author = "Adam Schenker and Mark Last and Horst Bunke and Abraham Kandel",
note = "Publisher Copyright: {\textcopyright} 2003 IEEE.; 7th International Conference on Document Analysis and Recognition, ICDAR 2003 ; Conference date: 03-08-2003 Through 06-08-2003",
year = "2003",
month = jan,
day = "1",
doi = "10.1109/ICDAR.2003.1227666",
language = "English",
series = "Proceedings of the International Conference on Document Analysis and Recognition, ICDAR",
publisher = "Institute of Electrical and Electronics Engineers",
pages = "240--244",
booktitle = "Proceedings - 7th International Conference on Document Analysis and Recognition, ICDAR 2003",
address = "United States",
}