{"id":"https://openalex.org/W1586806958","doi":"https://doi.org/10.1007/978-3-540-30192-9_53","title":"Clustering Structured Web Sources: A Schema-Based, Model-Differentiation Approach","display_name":"Clustering Structured Web Sources: A Schema-Based, Model-Differentiation Approach","publication_year":2004,"publication_date":"2004-01-01","ids":{"openalex":"https://openalex.org/W1586806958","doi":"https://doi.org/10.1007/978-3-540-30192-9_53","mag":"1586806958"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-540-30192-9_53","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-540-30192-9_53","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101494989","display_name":"Bin He","orcid":"https://orcid.org/0000-0001-7385-5542"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bin He","raw_affiliation_strings":["Computer Science Department, University of Illinois at Urbana-Champaign, Urbana, IL, 61801, USA","Computer Science Department, University of Illinois at Urbana Champaign, Urbana, IL#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Department, University of Illinois at Urbana-Champaign, Urbana, IL, 61801, USA","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"Computer Science Department, University of Illinois at Urbana Champaign, Urbana, IL#TAB#","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100401492","display_name":"Tao Tao","orcid":"https://orcid.org/0000-0001-6175-3071"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tao Tao","raw_affiliation_strings":["Computer Science Department, University of Illinois at Urbana-Champaign, Urbana, IL, 61801, USA","Computer Science Department, University of Illinois at Urbana Champaign, Urbana, IL#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Department, University of Illinois at Urbana-Champaign, Urbana, IL, 61801, USA","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"Computer Science Department, University of Illinois at Urbana Champaign, Urbana, IL#TAB#","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101880377","display_name":"Kevin Chen\u2013Chuan Chang","orcid":"https://orcid.org/0000-0003-0997-6803"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kevin Chen-Chuan Chang","raw_affiliation_strings":["Computer Science Department, University of Illinois at Urbana-Champaign, Urbana, IL, 61801, USA","Computer Science Department, University of Illinois at Urbana Champaign, Urbana, IL#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Department, University of Illinois at Urbana-Champaign, Urbana, IL, 61801, USA","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"Computer Science Department, University of Illinois at Urbana Champaign, Urbana, IL#TAB#","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I157725225"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":3.9415,"has_fulltext":false,"cited_by_count":30,"citation_normalized_percentile":{"value":0.94391972,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"536","last_page":"546"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9987000226974487,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9987000226974487,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.987500011920929,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9872999787330627,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8815950155258179},{"id":"https://openalex.org/keywords/schema","display_name":"Schema (genetic algorithms)","score":0.6966232061386108},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6685869693756104},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3638669550418854},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3476889729499817},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2858448028564453}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8815950155258179},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.6966232061386108},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6685869693756104},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3638669550418854},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3476889729499817},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2858448028564453}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/978-3-540-30192-9_53","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-540-30192-9_53","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.2.4471","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.2.4471","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://eagle.cs.uiuc.edu/pubs/2004/schemaclustering-clustweb04-htc-feb04.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1501500081","https://openalex.org/W1879587332","https://openalex.org/W1969831559","https://openalex.org/W1988413436","https://openalex.org/W1992419399","https://openalex.org/W2041674806","https://openalex.org/W2057712948","https://openalex.org/W2064686951","https://openalex.org/W2076983043","https://openalex.org/W2082503527","https://openalex.org/W2082583687","https://openalex.org/W2093390569","https://openalex.org/W2108489852","https://openalex.org/W2112719612","https://openalex.org/W2122943553","https://openalex.org/W2137845970","https://openalex.org/W2169044456","https://openalex.org/W2221553715","https://openalex.org/W4206765718","https://openalex.org/W4247346926"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W4402327032","https://openalex.org/W2382290278"],"abstract_inverted_index":null,"counts_by_year":[{"year":2016,"cited_by_count":1},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":3}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}