{"id":"https://openalex.org/W2163216397","doi":"https://doi.org/10.1017/s0269888914000216","title":"XML clustering: a review of structural approaches","display_name":"XML clustering: a review of structural approaches","publication_year":2014,"publication_date":"2014-10-29","ids":{"openalex":"https://openalex.org/W2163216397","doi":"https://doi.org/10.1017/s0269888914000216","mag":"2163216397"},"language":"en","primary_location":{"id":"doi:10.1017/s0269888914000216","is_oa":false,"landing_page_url":"https://doi.org/10.1017/s0269888914000216","pdf_url":null,"source":{"id":"https://openalex.org/S137506714","display_name":"The Knowledge Engineering Review","issn_l":"0269-8889","issn":["0269-8889","1469-8005"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311721","host_organization_name":"Cambridge University Press","host_organization_lineage":["https://openalex.org/P4310311721","https://openalex.org/P4310311702"],"host_organization_lineage_names":["Cambridge University Press","University of Cambridge"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Knowledge Engineering Review","raw_type":"journal-article"},"type":"review","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/A5041401789","display_name":"Maciej Piernik","orcid":"https://orcid.org/0000-0001-7281-284X"},"institutions":[{"id":"https://openalex.org/I46597724","display_name":"Pozna\u0144 University of Technology","ror":"https://ror.org/00p7p3302","country_code":"PL","type":"education","lineage":["https://openalex.org/I46597724"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Maciej Piernik","raw_affiliation_strings":["Institute of Computing Science, Poznan University of Technology, 60-965 Poznan, Poland; e-mail:","Pozna\u0144 University of  Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computing Science, Poznan University of Technology, 60-965 Poznan, Poland; e-mail:","institution_ids":["https://openalex.org/I46597724"]},{"raw_affiliation_string":"Pozna\u0144 University of  Technology","institution_ids":["https://openalex.org/I46597724"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060327349","display_name":"Dariusz Brzezi\u0144ski","orcid":"https://orcid.org/0000-0001-9723-525X"},"institutions":[{"id":"https://openalex.org/I46597724","display_name":"Pozna\u0144 University of Technology","ror":"https://ror.org/00p7p3302","country_code":"PL","type":"education","lineage":["https://openalex.org/I46597724"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Dariusz Brzezinski","raw_affiliation_strings":["Institute of Computing Science, Poznan University of Technology, 60-965 Poznan, Poland; e-mail:","Pozna\u0144 University of  Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computing Science, Poznan University of Technology, 60-965 Poznan, Poland; e-mail:","institution_ids":["https://openalex.org/I46597724"]},{"raw_affiliation_string":"Pozna\u0144 University of  Technology","institution_ids":["https://openalex.org/I46597724"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111998472","display_name":"Tadeusz Morzy","orcid":null},"institutions":[{"id":"https://openalex.org/I46597724","display_name":"Pozna\u0144 University of Technology","ror":"https://ror.org/00p7p3302","country_code":"PL","type":"education","lineage":["https://openalex.org/I46597724"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Tadeusz Morzy","raw_affiliation_strings":["Institute of Computing Science, Poznan University of Technology, 60-965 Poznan, Poland; e-mail:","Pozna\u0144 University of  Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computing Science, Poznan University of Technology, 60-965 Poznan, Poland; e-mail:","institution_ids":["https://openalex.org/I46597724"]},{"raw_affiliation_string":"Pozna\u0144 University of  Technology","institution_ids":["https://openalex.org/I46597724"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024977036","display_name":"Anna Le\u015bniewska","orcid":"https://orcid.org/0000-0003-3463-9622"},"institutions":[{"id":"https://openalex.org/I46597724","display_name":"Pozna\u0144 University of Technology","ror":"https://ror.org/00p7p3302","country_code":"PL","type":"education","lineage":["https://openalex.org/I46597724"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Anna Lesniewska","raw_affiliation_strings":["Institute of Computing Science, Poznan University of Technology, 60-965 Poznan, Poland; e-mail:","Pozna\u0144 University of  Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computing Science, Poznan University of Technology, 60-965 Poznan, Poland; e-mail:","institution_ids":["https://openalex.org/I46597724"]},{"raw_affiliation_string":"Pozna\u0144 University of  Technology","institution_ids":["https://openalex.org/I46597724"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I46597724"],"apc_list":null,"apc_paid":null,"fwci":2.5196,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.90914575,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"30","issue":"3","first_page":"297","last_page":"323"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.9975000023841858,"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"}},"topics":[{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.9975000023841858,"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/T11106","display_name":"Data Management and Algorithms","score":0.9947999715805054,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9923999905586243,"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":0.8282606601715088},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7739545106887817},{"id":"https://openalex.org/keywords/xml","display_name":"XML","score":0.7224773168563843},{"id":"https://openalex.org/keywords/markup-language","display_name":"Markup language","score":0.5755481719970703},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5332313179969788},{"id":"https://openalex.org/keywords/document-structure-description","display_name":"Document Structure Description","score":0.443392813205719},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.41775715351104736},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.32308995723724365},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.1971236765384674},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.19704443216323853}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.8282606601715088},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7739545106887817},{"id":"https://openalex.org/C8797682","wikidata":"https://www.wikidata.org/wiki/Q2115","display_name":"XML","level":2,"score":0.7224773168563843},{"id":"https://openalex.org/C45874996","wikidata":"https://www.wikidata.org/wiki/Q37045","display_name":"Markup language","level":3,"score":0.5755481719970703},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5332313179969788},{"id":"https://openalex.org/C68699486","wikidata":"https://www.wikidata.org/wiki/Q265904","display_name":"Document Structure Description","level":3,"score":0.443392813205719},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.41775715351104736},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.32308995723724365},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.1971236765384674},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.19704443216323853}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1017/s0269888914000216","is_oa":false,"landing_page_url":"https://doi.org/10.1017/s0269888914000216","pdf_url":null,"source":{"id":"https://openalex.org/S137506714","display_name":"The Knowledge Engineering Review","issn_l":"0269-8889","issn":["0269-8889","1469-8005"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311721","host_organization_name":"Cambridge University Press","host_organization_lineage":["https://openalex.org/P4310311721","https://openalex.org/P4310311702"],"host_organization_lineage_names":["Cambridge University Press","University of Cambridge"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Knowledge Engineering Review","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":105,"referenced_works":["https://openalex.org/W22683294","https://openalex.org/W23758216","https://openalex.org/W135761774","https://openalex.org/W259338706","https://openalex.org/W653955026","https://openalex.org/W847202544","https://openalex.org/W1480918727","https://openalex.org/W1486753193","https://openalex.org/W1493205727","https://openalex.org/W1494217862","https://openalex.org/W1504884927","https://openalex.org/W1505171204","https://openalex.org/W1522345903","https://openalex.org/W1530666358","https://openalex.org/W1547816897","https://openalex.org/W1549585131","https://openalex.org/W1552292059","https://openalex.org/W1564420957","https://openalex.org/W1565377632","https://openalex.org/W1565990971","https://openalex.org/W1569362407","https://openalex.org/W1572083646","https://openalex.org/W1572605355","https://openalex.org/W1592758009","https://openalex.org/W1608134647","https://openalex.org/W1628571627","https://openalex.org/W1660390307","https://openalex.org/W1673310716","https://openalex.org/W1700821439","https://openalex.org/W1845035324","https://openalex.org/W1925007459","https://openalex.org/W1958077162","https://openalex.org/W1967022996","https://openalex.org/W1971318281","https://openalex.org/W1975009259","https://openalex.org/W1976373002","https://openalex.org/W1977556410","https://openalex.org/W1980780450","https://openalex.org/W1985690171","https://openalex.org/W1987971958","https://openalex.org/W1990261244","https://openalex.org/W1991645955","https://openalex.org/W1991848143","https://openalex.org/W1992419399","https://openalex.org/W1995502855","https://openalex.org/W1998871699","https://openalex.org/W2003889154","https://openalex.org/W2008123298","https://openalex.org/W2008788779","https://openalex.org/W2011511839","https://openalex.org/W2016885468","https://openalex.org/W2022078289","https://openalex.org/W2024797550","https://openalex.org/W2027806969","https://openalex.org/W2030766291","https://openalex.org/W2033403400","https://openalex.org/W2047260621","https://openalex.org/W2048001624","https://openalex.org/W2049365470","https://openalex.org/W2049633694","https://openalex.org/W2055063781","https://openalex.org/W2057712948","https://openalex.org/W2064066237","https://openalex.org/W2068160960","https://openalex.org/W2081316297","https://openalex.org/W2090347585","https://openalex.org/W2099111195","https://openalex.org/W2102247866","https://openalex.org/W2103069411","https://openalex.org/W2103129584","https://openalex.org/W2104086170","https://openalex.org/W2107412086","https://openalex.org/W2107922666","https://openalex.org/W2108584692","https://openalex.org/W2111110587","https://openalex.org/W2113164419","https://openalex.org/W2116020486","https://openalex.org/W2127172217","https://openalex.org/W2128381480","https://openalex.org/W2131687179","https://openalex.org/W2134356404","https://openalex.org/W2139081439","https://openalex.org/W2140190241","https://openalex.org/W2150306348","https://openalex.org/W2153233077","https://openalex.org/W2160642098","https://openalex.org/W2160873337","https://openalex.org/W2163360598","https://openalex.org/W2164539421","https://openalex.org/W2171020494","https://openalex.org/W2295278941","https://openalex.org/W2461378853","https://openalex.org/W2477904557","https://openalex.org/W2482589566","https://openalex.org/W2487224391","https://openalex.org/W2504358273","https://openalex.org/W2517878783","https://openalex.org/W2953381786","https://openalex.org/W3036512766","https://openalex.org/W4231336072","https://openalex.org/W4236122429","https://openalex.org/W4246396312","https://openalex.org/W6623757938","https://openalex.org/W6657446499","https://openalex.org/W6675581698"],"related_works":["https://openalex.org/W4385386698","https://openalex.org/W4235354490","https://openalex.org/W2143258726","https://openalex.org/W2381082207","https://openalex.org/W2025266532","https://openalex.org/W2136793911","https://openalex.org/W1971521465","https://openalex.org/W2377737135","https://openalex.org/W2100702185","https://openalex.org/W2355331657"],"abstract_inverted_index":{"Abstract":[0],"With":[1],"its":[2],"presence":[3],"in":[4,23,81,134],"data":[5],"integration,":[6],"chemistry,":[7],"biological,":[8],"and":[9,45,76,93,103,126,131,158],"geographic":[10],"systems,":[11],"eXtensible":[12],"Markup":[13],"Language":[14],"(XML)":[15],"has":[16,41],"become":[17],"an":[18,135,140],"important":[19],"standard":[20],"not":[21],"only":[22],"computer":[24],"science.":[25],"A":[26],"common":[27,97],"problem":[28,75,89],"among":[29],"the":[30,48,74,78,88,95,110],"mentioned":[31],"applications":[32,157],"involves":[33],"structural":[34,64,100,145],"clustering":[35,104,121,147],"of":[36,50,53,63,143,161],"XML":[37,65,146],"documents\u2014an":[38],"issue":[39],"that":[40],"been":[42],"thoroughly":[43],"studied":[44],"led":[46],"to":[47,73,119,151],"creation":[49],"a":[51,60,70],"myriad":[52],"approaches.":[54],"In":[55,106],"this":[56,82],"paper,":[57],"we":[58,68,86,108,124,149],"present":[59,109],"comprehensive":[61],"review":[62],"clustering.":[66],"First,":[67],"provide":[69],"basic":[71],"introduction":[72],"highlight":[77],"main":[79],"challenges":[80],"research":[83],"area.":[84],"Subsequently,":[85],"divide":[87],"into":[90],"three":[91],"subtasks":[92],"discuss":[94],"most":[96,111],"document":[98],"representations,":[99],"similarity":[101],"measures,":[102,114],"algorithms.":[105],"addition,":[107],"popular":[112],"evaluation":[113],"which":[115],"can":[116],"be":[117],"used":[118],"estimate":[120],"quality.":[122],"Finally,":[123],"analyze":[125],"compare":[127],"23":[128],"state-of-the-art":[129],"approaches":[130],"arrange":[132],"them":[133],"original":[136],"taxonomy.":[137],"By":[138],"providing":[139],"up-to-date":[141],"analysis":[142],"existing":[144],"algorithms,":[148],"hope":[150],"showcase":[152],"methods":[153],"suitable":[154],"for":[155],"current":[156],"draw":[159],"lines":[160],"future":[162],"research.":[163]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":2}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}