{"id":"https://openalex.org/W2027806969","doi":"https://doi.org/10.1007/s10115-015-0820-0","title":"Clustering XML documents by patterns","display_name":"Clustering XML documents by patterns","publication_year":2015,"publication_date":"2015-01-23","ids":{"openalex":"https://openalex.org/W2027806969","doi":"https://doi.org/10.1007/s10115-015-0820-0","mag":"2027806969"},"language":"en","primary_location":{"id":"doi:10.1007/s10115-015-0820-0","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10115-015-0820-0","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10115-015-0820-0.pdf","source":{"id":"https://openalex.org/S81770430","display_name":"Knowledge and Information Systems","issn_l":"0219-1377","issn":["0219-1377","0219-3116"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Knowledge and Information Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s10115-015-0820-0.pdf","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":true,"raw_author_name":"Maciej Piernik","raw_affiliation_strings":["Institute of Computing Science, Poznan University of Technology, ul. Piotrowo 2, 60-965, Poznan, Poland","Institute of Computing Science, Pozna\u0144 University of Technology, Poznan, Poland 60-965#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computing Science, Poznan University of Technology, ul. Piotrowo 2, 60-965, Poznan, Poland","institution_ids":["https://openalex.org/I46597724"]},{"raw_affiliation_string":"Institute of Computing Science, Pozna\u0144 University of Technology, Poznan, Poland 60-965#TAB#","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, ul. Piotrowo 2, 60-965, Poznan, Poland","Institute of Computing Science, Pozna\u0144 University of Technology, Poznan, Poland 60-965#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computing Science, Poznan University of Technology, ul. Piotrowo 2, 60-965, Poznan, Poland","institution_ids":["https://openalex.org/I46597724"]},{"raw_affiliation_string":"Institute of Computing Science, Pozna\u0144 University of Technology, Poznan, Poland 60-965#TAB#","institution_ids":["https://openalex.org/I46597724"]}]},{"author_position":"last","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, ul. Piotrowo 2, 60-965, Poznan, Poland","Institute of Computing Science, Pozna\u0144 University of Technology, Poznan, Poland 60-965#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computing Science, Poznan University of Technology, ul. Piotrowo 2, 60-965, Poznan, Poland","institution_ids":["https://openalex.org/I46597724"]},{"raw_affiliation_string":"Institute of Computing Science, Pozna\u0144 University of Technology, Poznan, Poland 60-965#TAB#","institution_ids":["https://openalex.org/I46597724"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5041401789"],"corresponding_institution_ids":["https://openalex.org/I46597724"],"apc_list":{"value":2290,"currency":"EUR","value_usd":2890},"apc_paid":{"value":2290,"currency":"EUR","value_usd":2890},"fwci":4.9441,"has_fulltext":true,"cited_by_count":23,"citation_normalized_percentile":{"value":0.95165092,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"46","issue":"1","first_page":"185","last_page":"212"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9994000196456909,"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9994000196456909,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9993000030517578,"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":0.9976000189781189,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.8431249856948853},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7591450214385986},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.6973386406898499},{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"Pairwise comparison","score":0.5935678482055664},{"id":"https://openalex.org/keywords/xml","display_name":"XML","score":0.5662757158279419},{"id":"https://openalex.org/keywords/document-clustering","display_name":"Document clustering","score":0.4716816544532776},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4540953040122986},{"id":"https://openalex.org/keywords/document-structure-description","display_name":"Document Structure Description","score":0.4410068690776825},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4408004581928253},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.28281497955322266},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.05884775519371033}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.8431249856948853},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7591450214385986},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.6973386406898499},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.5935678482055664},{"id":"https://openalex.org/C8797682","wikidata":"https://www.wikidata.org/wiki/Q2115","display_name":"XML","level":2,"score":0.5662757158279419},{"id":"https://openalex.org/C177937566","wikidata":"https://www.wikidata.org/wiki/Q4223102","display_name":"Document clustering","level":3,"score":0.4716816544532776},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4540953040122986},{"id":"https://openalex.org/C68699486","wikidata":"https://www.wikidata.org/wiki/Q265904","display_name":"Document Structure Description","level":3,"score":0.4410068690776825},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4408004581928253},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.28281497955322266},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.05884775519371033},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s10115-015-0820-0","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10115-015-0820-0","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10115-015-0820-0.pdf","source":{"id":"https://openalex.org/S81770430","display_name":"Knowledge and Information Systems","issn_l":"0219-1377","issn":["0219-1377","0219-3116"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Knowledge and Information Systems","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s10115-015-0820-0","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10115-015-0820-0","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10115-015-0820-0.pdf","source":{"id":"https://openalex.org/S81770430","display_name":"Knowledge and Information Systems","issn_l":"0219-1377","issn":["0219-1377","0219-3116"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Knowledge and Information Systems","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2027806969.pdf","grobid_xml":"https://content.openalex.org/works/W2027806969.grobid-xml"},"referenced_works_count":45,"referenced_works":["https://openalex.org/W22683294","https://openalex.org/W75234989","https://openalex.org/W135761774","https://openalex.org/W154511698","https://openalex.org/W204278075","https://openalex.org/W847202544","https://openalex.org/W1486753193","https://openalex.org/W1523293200","https://openalex.org/W1547816897","https://openalex.org/W1548171311","https://openalex.org/W1549585131","https://openalex.org/W1565746575","https://openalex.org/W1565990971","https://openalex.org/W1572605355","https://openalex.org/W1592758009","https://openalex.org/W1628571627","https://openalex.org/W1664954303","https://openalex.org/W1679913846","https://openalex.org/W1845035324","https://openalex.org/W1956559956","https://openalex.org/W1965014786","https://openalex.org/W1974862676","https://openalex.org/W1993505169","https://openalex.org/W2003889154","https://openalex.org/W2016885468","https://openalex.org/W2026413985","https://openalex.org/W2038721957","https://openalex.org/W2046341811","https://openalex.org/W2047260621","https://openalex.org/W2069726734","https://openalex.org/W2098040986","https://openalex.org/W2103018059","https://openalex.org/W2103069411","https://openalex.org/W2107922666","https://openalex.org/W2113854849","https://openalex.org/W2116020486","https://openalex.org/W2124935488","https://openalex.org/W2150306348","https://openalex.org/W2159293599","https://openalex.org/W2160873337","https://openalex.org/W2163216397","https://openalex.org/W2165612380","https://openalex.org/W2295278941","https://openalex.org/W2325227998","https://openalex.org/W4235505822"],"related_works":["https://openalex.org/W2487162673","https://openalex.org/W2942366970","https://openalex.org/W2793211469","https://openalex.org/W2949152769","https://openalex.org/W4372354731","https://openalex.org/W2562400057","https://openalex.org/W1692008701","https://openalex.org/W2597588799","https://openalex.org/W4360593462","https://openalex.org/W2194570607"],"abstract_inverted_index":{"Now":[0],"that":[1,24],"the":[2,22,40,65,72,115,141,184],"use":[3,59],"of":[4,21,31,39,74,96,117,167,186],"XML":[5,41,170,197],"is":[6,35,114],"prevalent,":[7],"methods":[8],"for":[9,67],"mining":[10],"semi-structured":[11,33],"documents":[12,63,127],"have":[13],"become":[14],"even":[15],"more":[16],"important.":[17],"In":[18,51],"particular,":[19],"one":[20],"areas":[23],"could":[25],"greatly":[26],"benefit":[27],"from":[28],"in-depth":[29,188],"analysis":[30],"XML\u2019s":[32],"nature":[34],"cluster":[36,62,181],"analysis.":[37],"Most":[38],"clustering":[42,56,82,119,171],"approaches":[43,76],"developed":[44],"so":[45],"far":[46],"employ":[47],"pairwise":[48,68],"similarity":[49],"measures.":[50],"this":[52],"paper,":[53],"we":[54],"study":[55,190],"algorithms,":[57],"which":[58,86,123,150],"patterns":[60],"to":[61,88,125,129,163,192],"without":[64],"need":[66],"comparisons.":[69],"We":[70,138],"investigate":[71],"shortcomings":[73],"existing":[75],"and":[77,107,120,155,177],"establish":[78],"a":[79,100],"new":[80],"pattern-based":[81,196],"framework":[83,94],"called":[84,148],"XPattern,":[85],"tries":[87],"address":[89],"these":[90],"shortcomings.":[91],"The":[92,110],"proposed":[93,142],"consists":[95],"four":[97],"steps:":[98],"choosing":[99],"pattern":[101,103,105,118],"definition,":[102],"mining,":[104],"clustering,":[106],"document":[108],"assignment.":[109],"framework\u2019s":[111],"distinguishing":[112],"feature":[113],"combination":[116],"document-cluster":[121],"assignment,":[122],"allows":[124],"group":[126],"according":[128],"their":[130,135],"characteristic":[131],"features":[132],"rather":[133],"than":[134],"direct":[136],"similarity.":[137],"experimentally":[139],"evaluate":[140],"approach":[143],"by":[144],"implementing":[145],"an":[146,187],"algorithm":[147],"PathXP,":[149],"mines":[151],"maximal":[152],"frequent":[153],"paths":[154],"groups":[156],"them":[157],"into":[158],"profiles.":[159],"PathXP":[160],"was":[161],"found":[162],"match,":[164],"in":[165],"terms":[166],"accuracy,":[168],"other":[169],"approaches,":[172],"while":[173],"requiring":[174],"less":[175],"parametrization":[176],"providing":[178],"easily":[179],"interpretable":[180],"representatives.":[182],"Additionally,":[183],"results":[185],"experimental":[189],"lead":[191],"general":[193],"suggestions":[194],"concerning":[195],"clustering.":[198]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":2}],"updated_date":"2026-06-19T15:47:20.252518","created_date":"2025-10-10T00:00:00"}