Enhanced hypertext categorization using hyperlinks

Summary: Proposes robust statistical models with relaxation labeling to exploit hyperlinks for hypertext classification, mitigating noisy link signals in a local neighborhood. Demonstrates large gains over text-only classifiers on Yahoo and patent data, adapting to partial supervision with small labeled neighborhoods (error ~21%). (summarized by gpt-5-nano on Feb 09 2026)

Paper ID: 3085
Venue: SIGMOD
Year: 1998
Pagerank: 8.3307304e-05
Overall Rank: 2,624 | 82.00%
DOI: 10.1145/276304.276332

Incoming Non-self Citations Over Time

Authors

1. Soumen Chakrabarti (IBM)
2. Byron Dom (IBM)
3. Piotr Indyk (Stanford University)

BibTeX Citation

@inproceedings{chakrabarti_sigmod98,
        title = {{Enhanced hypertext categorization using hyperlinks}},
        author = {Chakrabarti, Soumen and Dom, Byron and Indyk, Piotr},
        series = {{SIGMOD} '98},
        booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
        publisher = {Association for Computing Machinery},
        doi = {10.1145/276304.276332},
        url = {https://dl.acm.org/doi/10.1145/276304.276332},
        year = {1998}
}

Incoming Citations (Sorted by Pagerank)

Showing 6 of 6 citing papers.

Rank	Citing Paper	Year	Venue	Pagerank
2,214	Computing Geographical Scopes of Web Resources	2000	VLDB	8.9409217e-05
3,383	Distributed Hypertext Resource Discovery Through Examples	1999	VLDB	7.4557297e-05
4,858	Building Hierarchical Classifiers Using Class Proximity	1999	VLDB	6.4751031e-05
8,166	Accurate and Efficient Crawling for Relevant Websites	2004	VLDB	5.4749372e-05
12,808	The BINGO! System for Information Portal Generation and Expert Web Search	2003	CIDR	5.093636e-05
12,884	Toward Learning Based Web Query Processing	2000	VLDB	5.093636e-05

Outgoing Citations (Sorted by Pagerank)

Showing 3 of 3 cited papers.

Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.

Rank	Cited Paper	Year	Venue	Pagerank
1,485	SPRINT: A Scalable Parallel Classifier for Data Mining	1996	VLDB	0.00010628998
1,858	Using Probabilistic Information in Data Integration	1997	VLDB	9.6035277e-05
5,145	Using taxonomy, discriminants, and signatures for navigating in text databases	1997	VLDB	6.3472692e-05

Semantically Similar Papers

#	Overall Rank	Paper	Year	Venue
1	14,126	Hypertext Databases and Data Mining*	1999	SIGMOD
2	12,862	Self-similarity in the web	2001	VLDB
3	4,689	LinkClus: Efficient Clustering via Heterogeneous Semantic Links	2006	VLDB
4	4,524	Probe, Count, and Classify: Categorizing Hidden-Web Databases	2001	SIGMOD
5	4,858	Building Hierarchical Classifiers Using Class Proximity	1999	VLDB
6	8,944	Efficient and Effective Metasearch for Text Databases Incorporating Linkages among Documents	2001	SIGMOD
7	3,383	Distributed Hypertext Resource Discovery Through Examples	1999	VLDB
8	14,009	A Method of Re-ranking Web Search Results Using their Hidden Hyperlink Structure	2002	VLDB
9	13,123	Indexing in a Hypertext Database	1990	VLDB
10	5,145	Using taxonomy, discriminants, and signatures for navigating in text databases	1997	VLDB