{"id":"https://openalex.org/W2735849377","doi":"https://doi.org/10.3233/web-170365","title":"Mining the information architecture of the WWW using automated website boundary detection","display_name":"Mining the information architecture of the WWW using automated website boundary detection","publication_year":2017,"publication_date":"2017-11-20","ids":{"openalex":"https://openalex.org/W2735849377","doi":"https://doi.org/10.3233/web-170365","mag":"2735849377"},"language":"en","primary_location":{"id":"doi:10.3233/web-170365","is_oa":false,"landing_page_url":"https://doi.org/10.3233/web-170365","pdf_url":null,"source":{"id":"https://openalex.org/S4210183871","display_name":"Web Intelligence","issn_l":"2405-6456","issn":["2405-6456","2405-6464"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Web Intelligence","raw_type":"journal-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/A5088264052","display_name":"Ayesh Alshukri","orcid":"https://orcid.org/0000-0003-0852-2068"},"institutions":[{"id":"https://openalex.org/I146655781","display_name":"University of Liverpool","ror":"https://ror.org/04xs57h96","country_code":"GB","type":"education","lineage":["https://openalex.org/I146655781"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Ayesh Alshukri","raw_affiliation_strings":["Department of Computer Science, University of Liverpool, Ashton Building, Ashton Street, L69 3BX, Liverpool, UK. E-mails:\u00a0,\u00a0","Department of Computer Science, University of Liverpool, Ashton Building, Ashton Street, L69 3BX, Liverpool, UK. E-mails:\u00a0a.alshukri@liverpool.ac.uk,\u00a0coenen@liverpool.ac.uk"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Liverpool, Ashton Building, Ashton Street, L69 3BX, Liverpool, UK. E-mails:\u00a0,\u00a0","institution_ids":["https://openalex.org/I146655781"]},{"raw_affiliation_string":"Department of Computer Science, University of Liverpool, Ashton Building, Ashton Street, L69 3BX, Liverpool, UK. E-mails:\u00a0a.alshukri@liverpool.ac.uk,\u00a0coenen@liverpool.ac.uk","institution_ids":["https://openalex.org/I146655781"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073606016","display_name":"Frans Coenen","orcid":"https://orcid.org/0000-0003-1026-6649"},"institutions":[{"id":"https://openalex.org/I146655781","display_name":"University of Liverpool","ror":"https://ror.org/04xs57h96","country_code":"GB","type":"education","lineage":["https://openalex.org/I146655781"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Frans Coenen","raw_affiliation_strings":["Department of Computer Science, University of Liverpool, Ashton Building, Ashton Street, L69 3BX, Liverpool, UK. E-mails:\u00a0,\u00a0","Department of Computer Science, University of Liverpool, Ashton Building, Ashton Street, L69 3BX, Liverpool, UK. E-mails:\u00a0a.alshukri@liverpool.ac.uk,\u00a0coenen@liverpool.ac.uk"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Liverpool, Ashton Building, Ashton Street, L69 3BX, Liverpool, UK. E-mails:\u00a0,\u00a0","institution_ids":["https://openalex.org/I146655781"]},{"raw_affiliation_string":"Department of Computer Science, University of Liverpool, Ashton Building, Ashton Street, L69 3BX, Liverpool, UK. E-mails:\u00a0a.alshukri@liverpool.ac.uk,\u00a0coenen@liverpool.ac.uk","institution_ids":["https://openalex.org/I146655781"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5088264052"],"corresponding_institution_ids":["https://openalex.org/I146655781"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.11836107,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"15","issue":"4","first_page":"269","last_page":"290"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9986000061035156,"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":0.9986000061035156,"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/T13976","display_name":"Web visibility and informetrics","score":0.9961000084877014,"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":0.9908999800682068,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7664379477500916},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6290906071662903},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.6054803729057312},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6007932424545288},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5526741147041321},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.5189292430877686},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.5149010419845581},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.500596284866333},{"id":"https://openalex.org/keywords/boundary","display_name":"Boundary (topology)","score":0.49185872077941895},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3262651562690735},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09645947813987732},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09559991955757141}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7664379477500916},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6290906071662903},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.6054803729057312},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6007932424545288},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5526741147041321},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.5189292430877686},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.5149010419845581},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.500596284866333},{"id":"https://openalex.org/C62354387","wikidata":"https://www.wikidata.org/wiki/Q875399","display_name":"Boundary (topology)","level":2,"score":0.49185872077941895},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3262651562690735},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09645947813987732},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09559991955757141},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","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/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3233/web-170365","is_oa":false,"landing_page_url":"https://doi.org/10.3233/web-170365","pdf_url":null,"source":{"id":"https://openalex.org/S4210183871","display_name":"Web Intelligence","issn_l":"2405-6456","issn":["2405-6456","2405-6464"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Web Intelligence","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":53,"referenced_works":["https://openalex.org/W44912151","https://openalex.org/W109201752","https://openalex.org/W140963759","https://openalex.org/W143174683","https://openalex.org/W174351557","https://openalex.org/W204891295","https://openalex.org/W1516791987","https://openalex.org/W1534051572","https://openalex.org/W1574303240","https://openalex.org/W1589502361","https://openalex.org/W1596290048","https://openalex.org/W1604901405","https://openalex.org/W1669209061","https://openalex.org/W1673310716","https://openalex.org/W1740509135","https://openalex.org/W1964119857","https://openalex.org/W2002531683","https://openalex.org/W2031497096","https://openalex.org/W2032304665","https://openalex.org/W2053377618","https://openalex.org/W2057017396","https://openalex.org/W2065168033","https://openalex.org/W2085470508","https://openalex.org/W2085922539","https://openalex.org/W2089458547","https://openalex.org/W2095293504","https://openalex.org/W2098486448","https://openalex.org/W2107324900","https://openalex.org/W2112800329","https://openalex.org/W2125050594","https://openalex.org/W2127218421","https://openalex.org/W2130854091","https://openalex.org/W2133459307","https://openalex.org/W2137102808","https://openalex.org/W2142604303","https://openalex.org/W2142838865","https://openalex.org/W2144982204","https://openalex.org/W2148748667","https://openalex.org/W2153137748","https://openalex.org/W2153192561","https://openalex.org/W2165612380","https://openalex.org/W2166601255","https://openalex.org/W2168165576","https://openalex.org/W2169470206","https://openalex.org/W2175110005","https://openalex.org/W2401383085","https://openalex.org/W2519011775","https://openalex.org/W3145128584","https://openalex.org/W4213060883","https://openalex.org/W4231080135","https://openalex.org/W4232332072","https://openalex.org/W4285719527","https://openalex.org/W6633452139"],"related_works":["https://openalex.org/W2611741382","https://openalex.org/W2588198209","https://openalex.org/W3135843367","https://openalex.org/W2613685774","https://openalex.org/W3112355890","https://openalex.org/W1909006023","https://openalex.org/W4205824991","https://openalex.org/W4220741973","https://openalex.org/W3200723557","https://openalex.org/W4312713546"],"abstract_inverted_index":{"The":[0,39,61],"world":[1],"wide":[2],"web":[3,19,31,78,164],"has":[4],"two":[5],"main":[6],"forms":[7],"of":[8,46,72,77,92,102,116,137,141],"architecture,":[9],"the":[10,22,30,44,70,74,88,90,114,144,163,177,185],"first":[11],"is":[12,15,24,27,41,52,67,95,120,130,169,182],"that":[13,25,51,80],"which":[14,26],"explicitly":[16],"encoded":[17],"into":[18],"pages,":[20],"and":[21,37,110,157,172,195],"second":[23],"implied":[28],"by":[29,43,133],"content,":[32],"particularly":[33],"pertaining":[34],"to":[35,99,166,179],"look":[36],"feel.":[38],"latter":[40],"exemplified":[42],"concept":[45,50,91],"a":[47,49,84,93,100,123,135],"website,":[48],"only":[53],"loosely":[54],"defined,":[55],"although":[56],"users":[57],"intuitively":[58],"understand":[59],"it.":[60],"Website":[62],"Boundary":[63],"Detection":[64],"(WBD)":[65],"problem":[66],"concerned":[68],"with":[69,97],"task":[71],"identifying":[73,134],"complete":[75],"collection":[76],"pages/resources":[79],"are":[81,155,191],"contained":[82],"within":[83],"single":[85],"website.":[86],"Whatever":[87],"case,":[89],"website":[94,106,124,136],"used":[96,168,181],"respect":[98],"number":[101],"application":[103],"domains":[104],"including;":[105],"archiving,":[107],"spam":[108],"detection,":[109],"www":[111],"analysis.":[112],"In":[113,149],"context":[115],"such":[117],"applications":[118],"it":[119],"beneficial":[121],"if":[122],"can":[125],"be":[126,167,180],"automatically":[127],"identified.":[128],"This":[129],"usually":[131],"done":[132],"interest":[138],"in":[139,193],"terms":[140],"its":[142],"boundary,":[143],"so":[145],"called":[146],"WBD":[147,153],"problem.":[148],"this":[150],"paper":[151],"seven":[152,189],"techniques":[154,161,175,190],"proposed":[156],"compared,":[158],"four":[159],"statistical":[160],"where":[162,176],"data":[165,178],"obtained":[170,183],"apriori,":[171],"three":[173],"dynamic":[174],"as":[184],"process":[186],"progresses.":[187],"All":[188],"presented":[192],"detail":[194],"evaluated.":[196]},"counts_by_year":[],"updated_date":"2026-03-03T06:13:14.889584","created_date":"2025-10-10T00:00:00"}