{"id":"https://openalex.org/W2153137748","doi":"https://doi.org/10.1109/wi.2003.1241204","title":"Mining Web site's clusters from link topology and site hierarchy","display_name":"Mining Web site's clusters from link topology and site hierarchy","publication_year":2004,"publication_date":"2004-04-23","ids":{"openalex":"https://openalex.org/W2153137748","doi":"https://doi.org/10.1109/wi.2003.1241204","mag":"2153137748"},"language":"en","primary_location":{"id":"doi:10.1109/wi.2003.1241204","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wi.2003.1241204","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings IEEE/WIC International Conference on Web Intelligence (WI 2003)","raw_type":"proceedings-article"},"type":"conference-paper","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":null,"display_name":"Kwok-Wai Cheung","orcid":null},"institutions":[{"id":"https://openalex.org/I141568987","display_name":"Hong Kong Baptist University","ror":"https://ror.org/0145fw131","country_code":"HK","type":"education","lineage":["https://openalex.org/I141568987"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Kwok-Wai Cheung","raw_affiliation_strings":["Department of Computer Science, Hong Kong Baptist University, Kowloon Tong, Hong Kong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Hong Kong Baptist University, Kowloon Tong, Hong Kong, China","institution_ids":["https://openalex.org/I141568987"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039935452","display_name":"Yuxiang Sun","orcid":"https://orcid.org/0000-0002-7704-0559"},"institutions":[{"id":"https://openalex.org/I141568987","display_name":"Hong Kong Baptist University","ror":"https://ror.org/0145fw131","country_code":"HK","type":"education","lineage":["https://openalex.org/I141568987"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yuxiang Sun","raw_affiliation_strings":["Department of Computer Science, Hong Kong Baptist University, Kowloon Tong, Hong Kong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Hong Kong Baptist University, Kowloon Tong, Hong Kong, China","institution_ids":["https://openalex.org/I141568987"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I141568987"],"apc_list":null,"apc_paid":null,"fwci":0.8622,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.73477407,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"31","issue":null,"first_page":"271","last_page":"277"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9993000030517578,"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":0.9993000030517578,"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/T10064","display_name":"Complex Network Analysis Techniques","score":0.9926999807357788,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11478","display_name":"Caching and Content Delivery","score":0.987500011920929,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.7550443410873413},{"id":"https://openalex.org/keywords/hyperlink","display_name":"Hyperlink","score":0.6423006057739258},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5766993761062622},{"id":"https://openalex.org/keywords/web-mining","display_name":"Web mining","score":0.5441629886627197},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.5431775450706482},{"id":"https://openalex.org/keywords/bipartite-graph","display_name":"Bipartite graph","score":0.5023632049560547},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.5010604858398438},{"id":"https://openalex.org/keywords/data-web","display_name":"Data Web","score":0.48626673221588135},{"id":"https://openalex.org/keywords/web-mapping","display_name":"Web mapping","score":0.4781932830810547},{"id":"https://openalex.org/keywords/web-modeling","display_name":"Web modeling","score":0.472319096326828},{"id":"https://openalex.org/keywords/web-site","display_name":"Web site","score":0.46036991477012634},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.45336252450942993},{"id":"https://openalex.org/keywords/hierarchy","display_name":"Hierarchy","score":0.45219314098358154},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.36698755621910095},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.3020419478416443},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.2591034770011902}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7550443410873413},{"id":"https://openalex.org/C30088001","wikidata":"https://www.wikidata.org/wiki/Q102014","display_name":"Hyperlink","level":3,"score":0.6423006057739258},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5766993761062622},{"id":"https://openalex.org/C197046077","wikidata":"https://www.wikidata.org/wiki/Q785337","display_name":"Web mining","level":3,"score":0.5441629886627197},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.5431775450706482},{"id":"https://openalex.org/C197657726","wikidata":"https://www.wikidata.org/wiki/Q174733","display_name":"Bipartite graph","level":3,"score":0.5023632049560547},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.5010604858398438},{"id":"https://openalex.org/C162005631","wikidata":"https://www.wikidata.org/wiki/Q54837","display_name":"Data Web","level":3,"score":0.48626673221588135},{"id":"https://openalex.org/C24733836","wikidata":"https://www.wikidata.org/wiki/Q649186","display_name":"Web mapping","level":4,"score":0.4781932830810547},{"id":"https://openalex.org/C130436687","wikidata":"https://www.wikidata.org/wiki/Q7978591","display_name":"Web modeling","level":3,"score":0.472319096326828},{"id":"https://openalex.org/C2984519610","wikidata":"https://www.wikidata.org/wiki/Q35127","display_name":"Web site","level":3,"score":0.46036991477012634},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.45336252450942993},{"id":"https://openalex.org/C31170391","wikidata":"https://www.wikidata.org/wiki/Q188619","display_name":"Hierarchy","level":2,"score":0.45219314098358154},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.36698755621910095},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.3020419478416443},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2591034770011902},{"id":"https://openalex.org/C34447519","wikidata":"https://www.wikidata.org/wiki/Q179522","display_name":"Market economy","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/wi.2003.1241204","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wi.2003.1241204","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings IEEE/WIC International Conference on Web Intelligence (WI 2003)","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.hkbu.edu.hk:hkbu_staff_publication-7577","is_oa":false,"landing_page_url":"https://repository.hkbu.edu.hk/hkbu_staff_publication/6495","pdf_url":null,"source":{"id":"https://openalex.org/S4377196872","display_name":"HKBU Institutional Repository (Hong Kong Baptist University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I141568987","host_organization_name":"Hong Kong Baptist University","host_organization_lineage":["https://openalex.org/I141568987"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"HKBU Staff Publication","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":19,"referenced_works":["https://openalex.org/W1600144774","https://openalex.org/W1828830618","https://openalex.org/W1989993068","https://openalex.org/W2008375984","https://openalex.org/W2013123195","https://openalex.org/W2063771604","https://openalex.org/W2065168033","https://openalex.org/W2079672501","https://openalex.org/W2080950999","https://openalex.org/W2088750139","https://openalex.org/W2088832942","https://openalex.org/W2092689128","https://openalex.org/W2101005742","https://openalex.org/W2102931907","https://openalex.org/W2115579680","https://openalex.org/W2138621811","https://openalex.org/W2151626491","https://openalex.org/W2153137748","https://openalex.org/W6682679482"],"related_works":["https://openalex.org/W2182629206","https://openalex.org/W2945931694","https://openalex.org/W4385950365","https://openalex.org/W2384444869","https://openalex.org/W3174726539","https://openalex.org/W2622968908","https://openalex.org/W2134078223","https://openalex.org/W2415191659","https://openalex.org/W4226367007","https://openalex.org/W2053028965"],"abstract_inverted_index":{"Foraging":[0],"information":[1,27],"in":[2,14],"large":[3],"and":[4,44,62,66,103],"complex":[5],"Web":[6,34,55,67,75,83,121,126],"sites":[7,35,122],"simply":[8],"using":[9,118],"keyword":[10],"search":[11,21],"usually":[12],"results":[13,136],"unpleasant":[15],"experience":[16],"due":[17,51],"to":[18,52,70],"the":[19,33,53,59,79,86,96,107,113,134],"overloaded":[20],"results.":[22,130],"To":[23],"support":[24],"more":[25],"effective":[26],"search,":[28],"some":[29],"descriptive":[30],"abstractions":[31],"of":[32,74,81,112,133],"(e.g.,":[36],"sitemaps)":[37],"are":[38,146],"mostly":[39],"needed.":[40],"However,":[41],"their":[42],"creation":[43],"maintenance":[45],"normally":[46],"requires":[47],"recurrent":[48],"manual":[49],"effort":[50],"fast-changing":[54],"contents.":[56],"We":[57],"extend":[58],"HITS":[60],"algorithm":[61,87,114],"integrate":[63],"hyperlink":[64],"topology":[65],"site":[68],"hierarchy":[69,73],"identify":[71],"a":[72,82],"page":[76],"clusters":[77],"as":[78,106,137,139],"abstraction":[80],"site.":[84],"As":[85],"is":[88],"based":[89],"on":[90],"HITS,":[91],"each":[92],"identified":[93],"cluster":[94,108],"follows":[95],"bipartite":[97],"graph":[98],"structure,":[99],"with":[100,128,142],"an":[101],"authority":[102],"hub":[104],"pair":[105],"summary.":[109],"The":[110],"effectiveness":[111],"has":[115],"been":[116],"evaluated":[117],"three":[119],"different":[120],"(containing":[123],"/spl":[124],"sim/6000-14000":[125],"pages)":[127],"promising":[129],"Detailed":[131],"interpretation":[132],"experimental":[135],"well":[138],"qualitative":[140],"comparison":[141],"other":[143],"related":[144],"works":[145],"also":[147],"included.":[148]},"counts_by_year":[{"year":2017,"cited_by_count":1},{"year":2014,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
