{"id":"https://openalex.org/W2136774890","doi":"https://doi.org/10.1109/wi.2003.1241201","title":"Detecting near-replicas on the Web by content and hyperlink analysis","display_name":"Detecting near-replicas on the Web by content and hyperlink analysis","publication_year":2004,"publication_date":"2004-04-23","ids":{"openalex":"https://openalex.org/W2136774890","doi":"https://doi.org/10.1109/wi.2003.1241201","mag":"2136774890"},"language":"en","primary_location":{"id":"doi:10.1109/wi.2003.1241201","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wi.2003.1241201","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":"https://openalex.org/A5016078483","display_name":"Ernesto Di Iorio","orcid":null},"institutions":[{"id":"https://openalex.org/I102064193","display_name":"University of Siena","ror":"https://ror.org/01tevnk56","country_code":"IT","type":"education","lineage":["https://openalex.org/I102064193"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"E. Di Iorio","raw_affiliation_strings":["Dipartimento di Ingegneria dellInformazione, Universit\u00e0 di Siena, Siena, Italy","Dipt. di Ingegneria dell' Informazione, Siena Univ., Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dipartimento di Ingegneria dellInformazione, Universit\u00e0 di Siena, Siena, Italy","institution_ids":["https://openalex.org/I102064193"]},{"raw_affiliation_string":"Dipt. di Ingegneria dell' Informazione, Siena Univ., Italy","institution_ids":["https://openalex.org/I102064193"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109267259","display_name":"Michelangelo Diligenti","orcid":null},"institutions":[{"id":"https://openalex.org/I102064193","display_name":"University of Siena","ror":"https://ror.org/01tevnk56","country_code":"IT","type":"education","lineage":["https://openalex.org/I102064193"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"M. Diligenti","raw_affiliation_strings":["Dipartimento di Ingegneria dellInformazione, Universit\u00e0 di Siena, Siena, Italy","Dipt. di Ingegneria dell' Informazione, Siena Univ., Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dipartimento di Ingegneria dellInformazione, Universit\u00e0 di Siena, Siena, Italy","institution_ids":["https://openalex.org/I102064193"]},{"raw_affiliation_string":"Dipt. di Ingegneria dell' Informazione, Siena Univ., Italy","institution_ids":["https://openalex.org/I102064193"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022658803","display_name":"Marco Gori","orcid":"https://orcid.org/0000-0001-6337-5430"},"institutions":[{"id":"https://openalex.org/I102064193","display_name":"University of Siena","ror":"https://ror.org/01tevnk56","country_code":"IT","type":"education","lineage":["https://openalex.org/I102064193"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"M. Gori","raw_affiliation_strings":["Dipartimento di Ingegneria dellInformazione, Universit\u00e0 di Siena, Siena, Italy","Dipt. di Ingegneria dell' Informazione, Siena Univ., Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dipartimento di Ingegneria dellInformazione, Universit\u00e0 di Siena, Siena, Italy","institution_ids":["https://openalex.org/I102064193"]},{"raw_affiliation_string":"Dipt. di Ingegneria dell' Informazione, Siena Univ., Italy","institution_ids":["https://openalex.org/I102064193"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080411641","display_name":"Marco Maggini","orcid":"https://orcid.org/0000-0002-6428-1265"},"institutions":[{"id":"https://openalex.org/I102064193","display_name":"University of Siena","ror":"https://ror.org/01tevnk56","country_code":"IT","type":"education","lineage":["https://openalex.org/I102064193"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"M. Maggini","raw_affiliation_strings":["Dipartimento di Ingegneria dellInformazione, Universit\u00e0 di Siena, Siena, Italy","Dipt. di Ingegneria dell' Informazione, Siena Univ., Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dipartimento di Ingegneria dellInformazione, Universit\u00e0 di Siena, Siena, Italy","institution_ids":["https://openalex.org/I102064193"]},{"raw_affiliation_string":"Dipt. di Ingegneria dell' Informazione, Siena Univ., Italy","institution_ids":["https://openalex.org/I102064193"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077324816","display_name":"Augusto Pucci","orcid":null},"institutions":[{"id":"https://openalex.org/I102064193","display_name":"University of Siena","ror":"https://ror.org/01tevnk56","country_code":"IT","type":"education","lineage":["https://openalex.org/I102064193"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"A. Pucci","raw_affiliation_strings":["Dipartimento di Ingegneria dellInformazione, Universit\u00e0 di Siena, Siena, Italy","Dipt. di Ingegneria dell' Informazione, Siena Univ., Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dipartimento di Ingegneria dellInformazione, Universit\u00e0 di Siena, Siena, Italy","institution_ids":["https://openalex.org/I102064193"]},{"raw_affiliation_string":"Dipt. di Ingegneria dell' Informazione, Siena Univ., Italy","institution_ids":["https://openalex.org/I102064193"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I102064193"],"apc_list":null,"apc_paid":null,"fwci":0.6466,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.68004491,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"249","last_page":"255"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9998000264167786,"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":0.9998000264167786,"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/T11478","display_name":"Caching and Content Delivery","score":0.9945999979972839,"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"}},{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9923999905586243,"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":0.8391927480697632},{"id":"https://openalex.org/keywords/hyperlink","display_name":"Hyperlink","score":0.7162188291549683},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.6179103255271912},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6116397976875305},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5801011919975281},{"id":"https://openalex.org/keywords/replication","display_name":"Replication (statistics)","score":0.45737504959106445},{"id":"https://openalex.org/keywords/signature","display_name":"Signature (topology)","score":0.43551722168922424},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.42319774627685547},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.4112367033958435},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0905090868473053}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8391927480697632},{"id":"https://openalex.org/C30088001","wikidata":"https://www.wikidata.org/wiki/Q102014","display_name":"Hyperlink","level":3,"score":0.7162188291549683},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.6179103255271912},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6116397976875305},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5801011919975281},{"id":"https://openalex.org/C12590798","wikidata":"https://www.wikidata.org/wiki/Q3933199","display_name":"Replication (statistics)","level":2,"score":0.45737504959106445},{"id":"https://openalex.org/C2779696439","wikidata":"https://www.wikidata.org/wiki/Q7512811","display_name":"Signature (topology)","level":2,"score":0.43551722168922424},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.42319774627685547},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.4112367033958435},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0905090868473053},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/wi.2003.1241201","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wi.2003.1241201","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:usiena-air.unisi.it:11365/36822","is_oa":false,"landing_page_url":"http://hdl.handle.net/11365/36822","pdf_url":null,"source":{"id":"https://openalex.org/S4377196319","display_name":"Use Siena air (University of Siena)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I102064193","host_organization_name":"University of Siena","host_organization_lineage":["https://openalex.org/I102064193"],"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"},{"id":"pmh:oai:usiena-air.unisi.it:11365/37959","is_oa":false,"landing_page_url":"http://hdl.handle.net/11365/37959","pdf_url":null,"source":{"id":"https://openalex.org/S4377196319","display_name":"Use Siena air (University of Siena)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I102064193","host_organization_name":"University of Siena","host_organization_lineage":["https://openalex.org/I102064193"],"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":16,"referenced_works":["https://openalex.org/W1516726196","https://openalex.org/W1531259569","https://openalex.org/W1941707302","https://openalex.org/W1956647075","https://openalex.org/W1997438973","https://openalex.org/W2066636486","https://openalex.org/W2070572105","https://openalex.org/W2087303323","https://openalex.org/W2118269922","https://openalex.org/W2147152072","https://openalex.org/W2152565070","https://openalex.org/W2169189540","https://openalex.org/W4250366158","https://openalex.org/W4285719527","https://openalex.org/W6632006871","https://openalex.org/W6667169455"],"related_works":["https://openalex.org/W17155033","https://openalex.org/W2245616560","https://openalex.org/W2351804282","https://openalex.org/W2048998278","https://openalex.org/W1556894713","https://openalex.org/W1490416172","https://openalex.org/W158130761","https://openalex.org/W2588706232","https://openalex.org/W2096877906","https://openalex.org/W2084041205"],"abstract_inverted_index":{"The":[0,86,103,127],"presence":[1,49],"of":[2,4,50,57,84,95,124,129,154],"near-replicas":[3,147],"documents":[5,52],"is":[6,79,89,106,133],"very":[7],"common":[8],"on":[9,81,143],"the":[10,26,46,48,55,63,96,100,114,117,122,130,144],"Web.":[11],"Documents":[12],"may":[13],"be":[14,30,149],"replicated":[15],"completely":[16],"or":[17,25],"partially":[18],"for":[19],"different":[20,33],"reasons":[21],"(versions,":[22],"mirrors,":[23],"etc.),":[24],"same":[27],"resource":[28],"can":[29,41,53,148],"associated":[31],"to":[32,69,120],"URLs":[34],"(dynamically":[35],"generated":[36],"pages,":[37,72],"etc.).":[38],"Whilst":[39],"replication":[40],"improve":[42],"information":[43],"accessibility":[44],"by":[45,91,108,137],"users,":[47],"near-replicated":[51],"hinder":[54],"effectiveness":[56],"search":[58],"engines":[59],"(for":[60],"example,":[61],"decreasing":[62],"coverage).":[64],"We":[65],"propose":[66],"a":[67,82,92,109,152],"method":[68],"detect":[70],"similar":[71],"in":[73],"particular":[74],"replicas":[75],"and":[76,135],"near-replicas,":[77],"which":[78,112,140],"based":[80],"pair":[83],"signatures.":[85],"first":[87],"signature":[88,105],"obtained":[90],"random":[93],"projection":[94],"bag-of-words":[97],"vector":[98],"representing":[99],"page":[101],"contents.":[102],"second":[104],"computed":[107],"recursive":[110],"equation":[111],"exploits":[113],"connectivity":[115],"among":[116],"Web":[118],"pages":[119],"code":[121],"context":[123],"each":[125],"page.":[126],"accuracy":[128],"proposed":[131],"approach":[132],"analyzed":[134],"validated":[136],"experimental":[138],"results":[139],"show":[141],"that":[142],"given":[145],"dataset":[146],"detected":[150],"with":[151],"precision-recall":[153],"93%.":[155]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}