Premium
Applying passage in Web text mining
Author(s) -
Theeramunkong Thanaruk
Publication year - 2004
Publication title -
international journal of intelligent systems
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.291
H-Index - 87
eISSN - 1098-111X
pISSN - 0884-8173
DOI - 10.1002/int.10158
Subject(s) - computer science , web mining , world wide web , information retrieval , the internet , web intelligence , web page , web modeling
Abstract Textual information on the Web is very huge, varied, and useful. Although traditional text mining treats a text document as a single piece of information, this approach may not be suitable for Web documents that are long and heterogeneous in their contents. This article presents a new approach that applies the concept of a passage to Web text mining. In this approach, a single Web text document is considered as several passages instead of a single text. To investigate the effectiveness of the approach, Thai Web documents taken from the Internet are used. As our preliminary experiment, we explore the influence of using passages on the construction of association rules by comparing them with a version that does not use passages. © 2004 Wiley Periodicals, Inc.