%0 Conference Paper %1 10.1007/978-3-642-13672-6_22 %A Lin, Cindy Xide %A Yu, Yintao %A Han, Jiawei %A Liu, Bing %B Advances in Knowledge Discovery and Data Mining %C Berlin, Heidelberg %D 2010 %E Zaki, Mohammed J. %E Yu, Jeffrey Xu %E Ravindran, B. %E Pudi, Vikram %I Springer Berlin Heidelberg %K clustering hierarchical hyperlink web %P 222--229 %T Hierarchical Web-Page Clustering via In-Page and Cross-Page Link Structures %X Despite of the wide diversity of web-pages, web-pages residing in a particular organization, in most cases, are organized with semantically hierarchic structures. For example, the website of a computer science department contains pages about its people, courses and research, among which pages of people are categorized into faculty, staff and students, and pages of research diversify into different areas. Uncovering such hierarchic structures could supply users a convenient way of comprehensive navigation and accelerate other web mining tasks. In this study, we extract a similarity matrix among pages via in-page and crosspage link structures, based on which a density-based clustering algorithm is developed, which hierarchically groups densely linked webpages into semantic clusters. Our experiments show that this method is efficient and effective, and sheds light on mining and exploring web structures. %@ 978-3-642-13672-6

@inproceedings{10.1007/978-3-642-13672-6_22, abstract = {Despite of the wide diversity of web-pages, web-pages residing in a particular organization, in most cases, are organized with semantically hierarchic structures. For example, the website of a computer science department contains pages about its people, courses and research, among which pages of people are categorized into faculty, staff and students, and pages of research diversify into different areas. Uncovering such hierarchic structures could supply users a convenient way of comprehensive navigation and accelerate other web mining tasks. In this study, we extract a similarity matrix among pages via in-page and crosspage link structures, based on which a density-based clustering algorithm is developed, which hierarchically groups densely linked webpages into semantic clusters. Our experiments show that this method is efficient and effective, and sheds light on mining and exploring web structures.}, added-at = {2020-09-30T11:55:41.000+0200}, address = {Berlin, Heidelberg}, author = {Lin, Cindy Xide and Yu, Yintao and Han, Jiawei and Liu, Bing}, biburl = {https://www.bibsonomy.org/bibtex/2fdf7ab7dcaa6598043782884f4cb976a/parismic}, booktitle = {Advances in Knowledge Discovery and Data Mining}, description = {Hierarchical Web-Page Clustering via In-Page and Cross-Page Link Structures | SpringerLink}, editor = {Zaki, Mohammed J. and Yu, Jeffrey Xu and Ravindran, B. and Pudi, Vikram}, interhash = {ff316d948860b82668a8224109c23b9b}, intrahash = {fdf7ab7dcaa6598043782884f4cb976a}, isbn = {978-3-642-13672-6}, keywords = {clustering hierarchical hyperlink web}, pages = {222--229}, publisher = {Springer Berlin Heidelberg}, timestamp = {2020-09-30T11:55:41.000+0200}, title = {Hierarchical Web-Page Clustering via In-Page and Cross-Page Link Structures}, year = 2010 }