{"id":"https://openalex.org/W2119710596","doi":"https://doi.org/10.1109/wse.2003.1234007","title":"Using keyword extraction for Web site clustering","display_name":"Using keyword extraction for Web site clustering","publication_year":2004,"publication_date":"2004-01-23","ids":{"openalex":"https://openalex.org/W2119710596","doi":"https://doi.org/10.1109/wse.2003.1234007","mag":"2119710596"},"language":"en","primary_location":{"id":"doi:10.1109/wse.2003.1234007","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wse.2003.1234007","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Fifth IEEE International Workshop on Web Site Evolution, 2003. Theme: Architecture. Proceedings.","raw_type":"proceedings-article"},"type":"article","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/A5025438762","display_name":"Paolo Tonella","orcid":"https://orcid.org/0000-0003-3088-0339"},"institutions":[{"id":"https://openalex.org/I4210094136","display_name":"Museo delle Scienze","ror":"https://ror.org/00qxmfv78","country_code":"IT","type":"archive","lineage":["https://openalex.org/I4210094136"]},{"id":"https://openalex.org/I4210097842","display_name":"Istituto Centrale per la Ricerca Scientifica e Tecnologica Applicata al Mare","ror":"https://ror.org/014cycx13","country_code":"IT","type":"facility","lineage":["https://openalex.org/I4210097842"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"P. Tonella","raw_affiliation_strings":["Centro per la Ricerca Scientifica e Tecnologica, ITC IRST, Povo, Italy","Centro per la Ricerca Scientifica e Tecnologica, Ist. Trentino di Cultura, Trento, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centro per la Ricerca Scientifica e Tecnologica, ITC IRST, Povo, Italy","institution_ids":["https://openalex.org/I4210097842"]},{"raw_affiliation_string":"Centro per la Ricerca Scientifica e Tecnologica, Ist. Trentino di Cultura, Trento, Italy","institution_ids":["https://openalex.org/I4210094136"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019306962","display_name":"Filippo Ricca","orcid":"https://orcid.org/0000-0002-3928-5408"},"institutions":[{"id":"https://openalex.org/I4210094136","display_name":"Museo delle Scienze","ror":"https://ror.org/00qxmfv78","country_code":"IT","type":"archive","lineage":["https://openalex.org/I4210094136"]},{"id":"https://openalex.org/I4210097842","display_name":"Istituto Centrale per la Ricerca Scientifica e Tecnologica Applicata al Mare","ror":"https://ror.org/014cycx13","country_code":"IT","type":"facility","lineage":["https://openalex.org/I4210097842"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"F. Ricca","raw_affiliation_strings":["Centro per la Ricerca Scientifica e Tecnologica, ITC IRST, Povo, Italy","Centro per la Ricerca Scientifica e Tecnologica, Ist. Trentino di Cultura, Trento, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centro per la Ricerca Scientifica e Tecnologica, ITC IRST, Povo, Italy","institution_ids":["https://openalex.org/I4210097842"]},{"raw_affiliation_string":"Centro per la Ricerca Scientifica e Tecnologica, Ist. Trentino di Cultura, Trento, Italy","institution_ids":["https://openalex.org/I4210094136"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091242580","display_name":"Emanuele Pianta","orcid":null},"institutions":[{"id":"https://openalex.org/I4210094136","display_name":"Museo delle Scienze","ror":"https://ror.org/00qxmfv78","country_code":"IT","type":"archive","lineage":["https://openalex.org/I4210094136"]},{"id":"https://openalex.org/I4210097842","display_name":"Istituto Centrale per la Ricerca Scientifica e Tecnologica Applicata al Mare","ror":"https://ror.org/014cycx13","country_code":"IT","type":"facility","lineage":["https://openalex.org/I4210097842"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"E. Pianta","raw_affiliation_strings":["Centro per la Ricerca Scientifica e Tecnologica, ITC IRST, Povo, Italy","Centro per la Ricerca Scientifica e Tecnologica, Ist. Trentino di Cultura, Trento, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centro per la Ricerca Scientifica e Tecnologica, ITC IRST, Povo, Italy","institution_ids":["https://openalex.org/I4210097842"]},{"raw_affiliation_string":"Centro per la Ricerca Scientifica e Tecnologica, Ist. Trentino di Cultura, Trento, Italy","institution_ids":["https://openalex.org/I4210094136"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113693081","display_name":"C. Girardi","orcid":null},"institutions":[{"id":"https://openalex.org/I4210094136","display_name":"Museo delle Scienze","ror":"https://ror.org/00qxmfv78","country_code":"IT","type":"archive","lineage":["https://openalex.org/I4210094136"]},{"id":"https://openalex.org/I4210097842","display_name":"Istituto Centrale per la Ricerca Scientifica e Tecnologica Applicata al Mare","ror":"https://ror.org/014cycx13","country_code":"IT","type":"facility","lineage":["https://openalex.org/I4210097842"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"C. Girardi","raw_affiliation_strings":["Centro per la Ricerca Scientifica e Tecnologica, ITC IRST, Povo, Italy","Centro per la Ricerca Scientifica e Tecnologica, Ist. Trentino di Cultura, Trento, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centro per la Ricerca Scientifica e Tecnologica, ITC IRST, Povo, Italy","institution_ids":["https://openalex.org/I4210097842"]},{"raw_affiliation_string":"Centro per la Ricerca Scientifica e Tecnologica, Ist. Trentino di Cultura, Trento, Italy","institution_ids":["https://openalex.org/I4210094136"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":16.9611,"has_fulltext":false,"cited_by_count":61,"citation_normalized_percentile":{"value":0.98759037,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"41","last_page":"48"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12601","display_name":"Web Applications and Data Management","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/T12601","display_name":"Web Applications and Data Management","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/T12016","display_name":"Web Data Mining and Analysis","score":0.9991000294685364,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9847000241279602,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.8321422338485718},{"id":"https://openalex.org/keywords/usable","display_name":"USable","score":0.7371232509613037},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7264904379844666},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.6624335646629333},{"id":"https://openalex.org/keywords/site-map","display_name":"Site map","score":0.620472252368927},{"id":"https://openalex.org/keywords/reverse-engineering","display_name":"Reverse engineering","score":0.5773007869720459},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.5605373978614807},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5382857322692871},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.46666568517684937},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4104892611503601},{"id":"https://openalex.org/keywords/static-web-page","display_name":"Static web page","score":0.3673722445964813},{"id":"https://openalex.org/keywords/web-development","display_name":"Web development","score":0.255009263753891},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.15523362159729004},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.11341014504432678},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08431100845336914}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8321422338485718},{"id":"https://openalex.org/C2780615836","wikidata":"https://www.wikidata.org/wiki/Q2471869","display_name":"USable","level":2,"score":0.7371232509613037},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7264904379844666},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.6624335646629333},{"id":"https://openalex.org/C67617509","wikidata":"https://www.wikidata.org/wiki/Q1503327","display_name":"Site map","level":5,"score":0.620472252368927},{"id":"https://openalex.org/C207850805","wikidata":"https://www.wikidata.org/wiki/Q269608","display_name":"Reverse engineering","level":2,"score":0.5773007869720459},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.5605373978614807},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5382857322692871},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.46666568517684937},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4104892611503601},{"id":"https://openalex.org/C173576120","wikidata":"https://www.wikidata.org/wiki/Q2641220","display_name":"Static web page","level":4,"score":0.3673722445964813},{"id":"https://openalex.org/C79373723","wikidata":"https://www.wikidata.org/wiki/Q386275","display_name":"Web development","level":3,"score":0.255009263753891},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.15523362159729004},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.11341014504432678},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08431100845336914},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/wse.2003.1234007","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wse.2003.1234007","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Fifth IEEE International Workshop on Web Site Evolution, 2003. Theme: Architecture. Proceedings.","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.108.4746","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.108.4746","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://tcc.itc.it/people/pianta/publications/wse2003clustKeywords.pdf","raw_type":"text"},{"id":"pmh:oai:iris.unige.it:11567/300169","is_oa":false,"landing_page_url":"http://hdl.handle.net/11567/300169","pdf_url":null,"source":{"id":"https://openalex.org/S4377196291","display_name":"CINECA IRIS Institutial Research Information System (University of Genoa)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I83816512","host_organization_name":"University of Genoa","host_organization_lineage":["https://openalex.org/I83816512"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1574901103","https://openalex.org/W1601724338","https://openalex.org/W1647641001","https://openalex.org/W1900564928","https://openalex.org/W1914987135","https://openalex.org/W2096393669","https://openalex.org/W2124378517","https://openalex.org/W2125000816","https://openalex.org/W2141801093","https://openalex.org/W2153597081","https://openalex.org/W2163506809","https://openalex.org/W2167809408","https://openalex.org/W4247316974","https://openalex.org/W6634260664"],"related_works":["https://openalex.org/W2064945795","https://openalex.org/W2156420263","https://openalex.org/W2088345472","https://openalex.org/W2008577673","https://openalex.org/W4385753583","https://openalex.org/W182781187","https://openalex.org/W2109933404","https://openalex.org/W2092706362","https://openalex.org/W2023856424","https://openalex.org/W2997495867"],"abstract_inverted_index":{"Reverse":[0],"engineering":[1],"techniques":[2],"have":[3],"the":[4,16,34,40,56,63,69,106,110,137,141,145],"potential":[5],"to":[6,49,79,123,129],"support":[7],"Web":[8,28,45,114],"site":[9,20,46],"understanding,":[10],"by":[11],"providing":[12],"views":[13],"that":[14,36,85],"show":[15],"organization":[17],"of":[18,43,58,83,109,112,118,136,144,148],"a":[19,31,44,89,101,113],"and":[21,51],"its":[22],"navigational":[23],"structure.":[24],"However,":[25],"representing":[26],"each":[27],"page":[29],"as":[30,88],"node":[32,91],"in":[33,65,92,140],"diagrams":[35],"are":[37,86],"recovered":[38,146],"from":[39],"source":[41],"code":[42],"leads":[47],"often":[48],"huge":[50],"unreadable":[52],"graphs.":[53],"Moreover,":[54],"since":[55],"level":[57],"connectivity":[59],"is":[60,121,127,139],"typically":[61],"high,":[62],"edges":[64],"such":[66],"graphs":[67],"make":[68],"overall":[70],"result":[71],"still":[72],"less":[73],"usable.":[74],"Clustering":[75],"can":[76],"be":[77],"used":[78],"produce":[80],"cohesive":[81],"groups":[82],"pages":[84,131],"displayed":[87],"single":[90],"reverse":[93],"engineered":[94],"diagrams.":[95],"In":[96],"this":[97],"paper,":[98],"we":[99],"propose":[100],"clustering":[102],"method":[103],"based":[104],"on":[105],"automatic":[107,142],"extraction":[108],"keywords":[111,120,138],"page.":[115],"The":[116],"presence":[117],"common":[119],"exploited":[122],"decide":[124],"when":[125],"it":[126],"appropriate":[128],"group":[130],"together.":[132],"A":[133],"second":[134],"usage":[135],"labeling":[143],"clusters":[147],"pages.":[149]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":6},{"year":2012,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
