{"id":"https://openalex.org/W2052794381","doi":"https://doi.org/10.1109/wse.2007.4380246","title":"Clustering Algorithms and Latent Semantic Indexing to Identify Similar Pages in Web Applications","display_name":"Clustering Algorithms and Latent Semantic Indexing to Identify Similar Pages in Web Applications","publication_year":2007,"publication_date":"2007-10-01","ids":{"openalex":"https://openalex.org/W2052794381","doi":"https://doi.org/10.1109/wse.2007.4380246","mag":"2052794381"},"language":"en","primary_location":{"id":"doi:10.1109/wse.2007.4380246","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wse.2007.4380246","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2007 9th IEEE International Workshop on Web Site Evolution","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":"https://openalex.org/A5079088548","display_name":"Andrea De Lucia","orcid":"https://orcid.org/0000-0002-4238-1425"},"institutions":[{"id":"https://openalex.org/I131729948","display_name":"University of Salerno","ror":"https://ror.org/0192m2k53","country_code":"IT","type":"education","lineage":["https://openalex.org/I131729948"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Andrea de Lucia","raw_affiliation_strings":["Dipartimento di Matematica e Informatica, University of Salerno, Fisciano, Italy","Univ. of Salerno, Fisciano"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dipartimento di Matematica e Informatica, University of Salerno, Fisciano, Italy","institution_ids":["https://openalex.org/I131729948"]},{"raw_affiliation_string":"Univ. of Salerno, Fisciano","institution_ids":["https://openalex.org/I131729948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023477042","display_name":"Michele Risi","orcid":"https://orcid.org/0000-0003-1114-3480"},"institutions":[{"id":"https://openalex.org/I131729948","display_name":"University of Salerno","ror":"https://ror.org/0192m2k53","country_code":"IT","type":"education","lineage":["https://openalex.org/I131729948"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Michele Risi","raw_affiliation_strings":["Dipartimento di Matematica e Informatica, University of Salerno, Fisciano, Italy","Univ. of Salerno, Fisciano"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dipartimento di Matematica e Informatica, University of Salerno, Fisciano, Italy","institution_ids":["https://openalex.org/I131729948"]},{"raw_affiliation_string":"Univ. of Salerno, Fisciano","institution_ids":["https://openalex.org/I131729948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074856207","display_name":"Genoveffa Tortora","orcid":"https://orcid.org/0000-0003-4765-8371"},"institutions":[{"id":"https://openalex.org/I131729948","display_name":"University of Salerno","ror":"https://ror.org/0192m2k53","country_code":"IT","type":"education","lineage":["https://openalex.org/I131729948"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Genoveffa Tortora","raw_affiliation_strings":["Dipartimento di Matematica e Informatica, University of Salerno, Fisciano, Italy","Univ. of Salerno, Fisciano"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dipartimento di Matematica e Informatica, University of Salerno, Fisciano, Italy","institution_ids":["https://openalex.org/I131729948"]},{"raw_affiliation_string":"Univ. of Salerno, Fisciano","institution_ids":["https://openalex.org/I131729948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082957347","display_name":"Giuseppe Scanniello","orcid":"https://orcid.org/0000-0003-0024-7508"},"institutions":[{"id":"https://openalex.org/I20272500","display_name":"University of Basilicata","ror":"https://ror.org/03tc05689","country_code":"IT","type":"education","lineage":["https://openalex.org/I20272500"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Giuseppe Scanniello","raw_affiliation_strings":["Dipartimento di Matematica e Informatica, University of Basilicata, Rome, Italy","Dipartimento di Matematica e Informatica, University of Basilicata, Viale Dell'Ateneo, Macchia, Romana, 85100, Potenza, ITALY, giuseppe.scanniello@unibas.it#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dipartimento di Matematica e Informatica, University of Basilicata, Rome, Italy","institution_ids":["https://openalex.org/I20272500"]},{"raw_affiliation_string":"Dipartimento di Matematica e Informatica, University of Basilicata, Viale Dell'Ateneo, Macchia, Romana, 85100, Potenza, ITALY, giuseppe.scanniello@unibas.it#TAB#","institution_ids":["https://openalex.org/I20272500"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"31","issue":null,"first_page":"65","last_page":"72"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9955999851226807,"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/T10260","display_name":"Software Engineering Research","score":0.9921000003814697,"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/cluster-analysis","display_name":"Cluster analysis","score":0.7999056577682495},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7815954685211182},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.5930434465408325},{"id":"https://openalex.org/keywords/hierarchical-clustering","display_name":"Hierarchical clustering","score":0.5098046660423279},{"id":"https://openalex.org/keywords/correlation-clustering","display_name":"Correlation clustering","score":0.4978504180908203},{"id":"https://openalex.org/keywords/canopy-clustering-algorithm","display_name":"Canopy clustering algorithm","score":0.4865761995315552},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4826224744319916},{"id":"https://openalex.org/keywords/cure-data-clustering-algorithm","display_name":"CURE data clustering algorithm","score":0.47836369276046753},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.44570812582969666},{"id":"https://openalex.org/keywords/document-clustering","display_name":"Document clustering","score":0.4435175657272339},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33590757846832275},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.1348859667778015}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7999056577682495},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7815954685211182},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.5930434465408325},{"id":"https://openalex.org/C92835128","wikidata":"https://www.wikidata.org/wiki/Q1277447","display_name":"Hierarchical clustering","level":3,"score":0.5098046660423279},{"id":"https://openalex.org/C94641424","wikidata":"https://www.wikidata.org/wiki/Q5172845","display_name":"Correlation clustering","level":3,"score":0.4978504180908203},{"id":"https://openalex.org/C104047586","wikidata":"https://www.wikidata.org/wiki/Q5033439","display_name":"Canopy clustering algorithm","level":4,"score":0.4865761995315552},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4826224744319916},{"id":"https://openalex.org/C33704608","wikidata":"https://www.wikidata.org/wiki/Q5014717","display_name":"CURE data clustering algorithm","level":4,"score":0.47836369276046753},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.44570812582969666},{"id":"https://openalex.org/C177937566","wikidata":"https://www.wikidata.org/wiki/Q4223102","display_name":"Document clustering","level":3,"score":0.4435175657272339},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33590757846832275},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.1348859667778015}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/wse.2007.4380246","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wse.2007.4380246","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2007 9th IEEE International Workshop on Web Site Evolution","raw_type":"proceedings-article"},{"id":"pmh:oai:iris.unibas.it:11563/13688","is_oa":false,"landing_page_url":"http://hdl.handle.net/11563/13688","pdf_url":null,"source":{"id":"https://openalex.org/S4377196360","display_name":"CINECA IRIS Institutional Research Information System (University of Basilicata)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I20272500","host_organization_name":"University of Basilicata","host_organization_lineage":["https://openalex.org/I20272500"],"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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W65738273","https://openalex.org/W106960782","https://openalex.org/W1508506413","https://openalex.org/W1647641001","https://openalex.org/W1885561873","https://openalex.org/W1900564928","https://openalex.org/W1992419399","https://openalex.org/W2000432226","https://openalex.org/W2026836928","https://openalex.org/W2083336425","https://openalex.org/W2096393669","https://openalex.org/W2100872652","https://openalex.org/W2116587605","https://openalex.org/W2116630138","https://openalex.org/W2119160783","https://openalex.org/W2124957865","https://openalex.org/W2132085569","https://openalex.org/W2147152072","https://openalex.org/W2153597081","https://openalex.org/W2153717260","https://openalex.org/W2160172778","https://openalex.org/W2799061466","https://openalex.org/W2911779492","https://openalex.org/W2999729612","https://openalex.org/W4230663420","https://openalex.org/W4239961266","https://openalex.org/W6630437125","https://openalex.org/W6677880244","https://openalex.org/W6758093478","https://openalex.org/W7014191107","https://openalex.org/W7019129576"],"related_works":["https://openalex.org/W2559422900","https://openalex.org/W3144143113","https://openalex.org/W4306940721","https://openalex.org/W3022637481","https://openalex.org/W3120229345","https://openalex.org/W2160785859","https://openalex.org/W2491448268","https://openalex.org/W2384052049","https://openalex.org/W4220814143","https://openalex.org/W2087424554"],"abstract_inverted_index":{"In":[0,115],"this":[1,24,82],"paper,":[2],"we":[3,26,122],"analyze":[4],"some":[5],"clustering":[6,75,93,97,101,109],"algorithms":[7],"that":[8,35,51],"have":[9,27,123],"been":[10],"widely":[11,105],"employed":[12,106],"in":[13],"the":[14,18,41,54,90,119,125],"past":[15],"to":[16,31,117],"support":[17],"comprehension":[19],"of":[20,81,89,128],"Web":[21,57,130,135],"applications.":[22],"To":[23],"end,":[25],"defined":[28],"an":[29],"approach":[30,45],"identify":[32],"static":[33,126,134],"pages":[34,58,73,127],"are":[36],"duplicated":[37],"or":[38],"cloned":[39],"at":[40],"content":[42],"level.":[43],"This":[44],"is":[46],"based":[47,85],"on":[48,86],"a":[49,63,95,104],"process":[50],"first":[52],"computes":[53],"dissimilarity":[55],"between":[56],"using":[59,74],"latent":[60],"semantic":[61],"indexing,":[62],"well":[64],"known":[65],"information":[66],"retrieval":[67],"technique,":[68],"and":[69,103,132],"then":[70],"groups":[71],"similar":[72],"algorithms.":[76],"We":[77],"consider":[78],"five":[79],"instances":[80],"process,":[83],"each":[84],"three":[87,129],"variants":[88],"agglomerative":[91],"hierarchical":[92],"algorithm,":[94,98,102,110],"divisive":[96],"k-means":[99],"partitional":[100,107],"competitive":[108],"namely":[111],"Winner":[112],"Takes":[113],"All.":[114],"order":[116],"assess":[118],"proposed":[120],"approach,":[121],"used":[124],"applications":[131],"one":[133],"site.":[136]},"counts_by_year":[{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
