{"id":"https://openalex.org/W2153717260","doi":"https://doi.org/10.1109/wpc.2004.1311062","title":"An empirical study on keyword-based web site clustering","display_name":"An empirical study on keyword-based web site clustering","publication_year":2004,"publication_date":"2004-11-13","ids":{"openalex":"https://openalex.org/W2153717260","doi":"https://doi.org/10.1109/wpc.2004.1311062","mag":"2153717260"},"language":"en","primary_location":{"id":"doi:10.1109/wpc.2004.1311062","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wpc.2004.1311062","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings. 12th IEEE International Workshop on Program Comprehension, 2004.","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/A5019306962","display_name":"Filippo Ricca","orcid":"https://orcid.org/0000-0002-3928-5408"},"institutions":[{"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":["ITC-IRST-Centro per la Ricerca Scientifica e Tecnologica, Trento, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ITC-IRST-Centro per la Ricerca Scientifica e Tecnologica, Trento, Italy","institution_ids":["https://openalex.org/I4210097842"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025438762","display_name":"Paolo Tonella","orcid":"https://orcid.org/0000-0003-3088-0339"},"institutions":[{"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":["ITC-IRST-Centro per la Ricerca Scientifica e Tecnologica, Trento, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ITC-IRST-Centro per la Ricerca Scientifica e Tecnologica, Trento, Italy","institution_ids":["https://openalex.org/I4210097842"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113693081","display_name":"C. Girardi","orcid":null},"institutions":[{"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":["ITC-IRST-Centro per la Ricerca Scientifica e Tecnologica, Trento, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ITC-IRST-Centro per la Ricerca Scientifica e Tecnologica, Trento, Italy","institution_ids":["https://openalex.org/I4210097842"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091242580","display_name":"Emanuele Pianta","orcid":null},"institutions":[{"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":["ITC-IRST-Centro per la Ricerca Scientifica e Tecnologica, Trento, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ITC-IRST-Centro per la Ricerca Scientifica e Tecnologica, Trento, Italy","institution_ids":["https://openalex.org/I4210097842"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":7.269,"has_fulltext":false,"cited_by_count":26,"citation_normalized_percentile":{"value":0.96661271,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"204","last_page":"213"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9988999962806702,"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":0.9988999962806702,"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/T10679","display_name":"Service-Oriented Architecture and Web Services","score":0.9975000023841858,"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/T12601","display_name":"Web Applications and Data Management","score":0.9940999746322632,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8498182892799377},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6985564231872559},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6879367828369141},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.6164044737815857},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.6009389758110046},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5244619846343994},{"id":"https://openalex.org/keywords/web-mining","display_name":"Web mining","score":0.499370813369751},{"id":"https://openalex.org/keywords/web-modeling","display_name":"Web modeling","score":0.4443942904472351},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4350476861000061},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.199691504240036},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08114591240882874}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8498182892799377},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6985564231872559},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6879367828369141},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.6164044737815857},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.6009389758110046},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5244619846343994},{"id":"https://openalex.org/C197046077","wikidata":"https://www.wikidata.org/wiki/Q785337","display_name":"Web mining","level":3,"score":0.499370813369751},{"id":"https://openalex.org/C130436687","wikidata":"https://www.wikidata.org/wiki/Q7978591","display_name":"Web modeling","level":3,"score":0.4443942904472351},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4350476861000061},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.199691504240036},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08114591240882874},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/wpc.2004.1311062","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wpc.2004.1311062","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings. 12th IEEE International Workshop on Program Comprehension, 2004.","raw_type":"proceedings-article"},{"id":"pmh:oai:iris.unige.it:11567/300176","is_oa":false,"landing_page_url":"http://hdl.handle.net/11567/300176","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":"","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7400000095367432,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1490674333","https://openalex.org/W1574901103","https://openalex.org/W1601724338","https://openalex.org/W1647641001","https://openalex.org/W1833785989","https://openalex.org/W1900564928","https://openalex.org/W1914987135","https://openalex.org/W1956559956","https://openalex.org/W2096393669","https://openalex.org/W2111643214","https://openalex.org/W2116630138","https://openalex.org/W2119710596","https://openalex.org/W2124378517","https://openalex.org/W2125000816","https://openalex.org/W2126129257","https://openalex.org/W2141801093","https://openalex.org/W2145036943","https://openalex.org/W2148350542","https://openalex.org/W2148484494","https://openalex.org/W2153597081","https://openalex.org/W2163506809","https://openalex.org/W2167809408","https://openalex.org/W2325227998","https://openalex.org/W4241755296","https://openalex.org/W4247316974","https://openalex.org/W4251218026","https://openalex.org/W6629329164"],"related_works":["https://openalex.org/W2945931694","https://openalex.org/W132269582","https://openalex.org/W2622968908","https://openalex.org/W2386849321","https://openalex.org/W3174726539","https://openalex.org/W2083329789","https://openalex.org/W2137912379","https://openalex.org/W2134078223","https://openalex.org/W2182629206","https://openalex.org/W2415191659"],"abstract_inverted_index":{"Web":[0,38,45,59,97,108],"site":[1],"evolution":[2],"is":[3,30,48],"characterized":[4],"by":[5],"a":[6,49,77,116,126],"limited":[7],"support":[8],"to":[9,14,31,92,133,142],"the":[10,15,41,44,67,94,104,107,130,135,143],"understanding":[11],"activities":[12],"offered":[13],"developers.":[16],"In":[17],"fact,":[18],"design":[19],"diagrams":[20],"are":[21],"often":[22],"missing":[23],"or":[24],"outdated.":[25],"A":[26],"potentially":[27],"interesting":[28],"option":[29],"reverse":[32],"engineer":[33],"high":[34],"level":[35],"views":[36],"of":[37,43,69,79,99,106,129,137],"sites":[39],"from":[40,103],"content":[42,120],"pages.":[46],"Clustering":[47],"valuable":[50],"technique":[51],"that":[52,89],"can":[53,61],"be":[54,62],"used":[55],"in":[56,119],"this":[57],"respect.":[58],"pages":[60],"clustered":[63],"together":[64],"based":[65],"on":[66],"similarity":[68],"summary":[70],"information":[71],"about":[72],"their":[73],"content,":[74],"represented":[75],"as":[76],"list":[78],"automatically":[80,101],"extracted":[81],"keywords.":[82],"This":[83],"work":[84],"presents":[85],"an":[86],"empirical":[87],"study":[88,131],"was":[90,132],"conducted":[91],"determine":[93],"meaningfulness":[95],"for":[96],"developers":[98],"clusters":[100],"produced":[102],"analysis":[105,121],"page":[109],"content.":[110],"Natural":[111],"language":[112],"processing":[113],"(NLP)":[114],"plays":[115],"central":[117],"role":[118],"and":[122],"keyword":[123],"extraction.":[124],"Thus,":[125],"second":[127],"objective":[128],"assess":[134],"contribution":[136],"some":[138],"shallow":[139],"NLP":[140],"techniques":[141],"clustering":[144],"task.":[145]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
