{"id":"https://openalex.org/W2904793415","doi":"https://doi.org/10.3390/data3040066","title":"Similar Text Fragments Extraction for Identifying Common Wikipedia Communities","display_name":"Similar Text Fragments Extraction for Identifying Common Wikipedia Communities","publication_year":2018,"publication_date":"2018-12-13","ids":{"openalex":"https://openalex.org/W2904793415","doi":"https://doi.org/10.3390/data3040066","mag":"2904793415"},"language":"en","primary_location":{"id":"doi:10.3390/data3040066","is_oa":true,"landing_page_url":"https://doi.org/10.3390/data3040066","pdf_url":null,"source":{"id":"https://openalex.org/S4210226510","display_name":"Data","issn_l":"2306-5729","issn":["2306-5729"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Data","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.3390/data3040066","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5061829636","display_name":"Svitlana Petrasova","orcid":"https://orcid.org/0000-0001-6011-135X"},"institutions":[{"id":"https://openalex.org/I67256668","display_name":"National Technical University \"Kharkiv Polytechnic Institute\"","ror":"https://ror.org/00yp5c433","country_code":"UA","type":"education","lineage":["https://openalex.org/I67256668"]}],"countries":["UA"],"is_corresponding":true,"raw_author_name":"Svitlana Petrasova","raw_affiliation_strings":["Department of Intelligent Computer Systems, National Technical University \u201cKharkiv Polytechnic Institute\u201d, 61002 Kharkiv, Ukraine","Department of Intelligent Computer Systems, National Technical University \"Kharkiv Polytechnic Institute\", 61002 Kharkiv, Ukraine"],"raw_orcid":"https://orcid.org/0000-0001-6011-135X","affiliations":[{"raw_affiliation_string":"Department of Intelligent Computer Systems, National Technical University \u201cKharkiv Polytechnic Institute\u201d, 61002 Kharkiv, Ukraine","institution_ids":["https://openalex.org/I67256668"]},{"raw_affiliation_string":"Department of Intelligent Computer Systems, National Technical University \"Kharkiv Polytechnic Institute\", 61002 Kharkiv, Ukraine","institution_ids":["https://openalex.org/I67256668"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081869570","display_name":"Nina Khairova","orcid":"https://orcid.org/0000-0002-9826-0286"},"institutions":[{"id":"https://openalex.org/I67256668","display_name":"National Technical University \"Kharkiv Polytechnic Institute\"","ror":"https://ror.org/00yp5c433","country_code":"UA","type":"education","lineage":["https://openalex.org/I67256668"]}],"countries":["UA"],"is_corresponding":true,"raw_author_name":"Nina Khairova","raw_affiliation_strings":["Department of Intelligent Computer Systems, National Technical University \u201cKharkiv Polytechnic Institute\u201d, 61002 Kharkiv, Ukraine","Department of Intelligent Computer Systems, National Technical University \"Kharkiv Polytechnic Institute\", 61002 Kharkiv, Ukraine"],"raw_orcid":"https://orcid.org/0000-0002-9826-0286","affiliations":[{"raw_affiliation_string":"Department of Intelligent Computer Systems, National Technical University \u201cKharkiv Polytechnic Institute\u201d, 61002 Kharkiv, Ukraine","institution_ids":["https://openalex.org/I67256668"]},{"raw_affiliation_string":"Department of Intelligent Computer Systems, National Technical University \"Kharkiv Polytechnic Institute\", 61002 Kharkiv, Ukraine","institution_ids":["https://openalex.org/I67256668"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056656799","display_name":"W\u0142odzimierz Lewoniewski","orcid":"https://orcid.org/0000-0002-0163-5492"},"institutions":[{"id":"https://openalex.org/I12379730","display_name":"Pozna\u0144 University of Economics and Business","ror":"https://ror.org/0532c1x92","country_code":"PL","type":"education","lineage":["https://openalex.org/I12379730"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"W\u0142odzimierz Lewoniewski","raw_affiliation_strings":["Department of Information Systems, Poznan University of Economics and Business, 61-875 Poznan, Poland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information Systems, Poznan University of Economics and Business, 61-875 Poznan, Poland","institution_ids":["https://openalex.org/I12379730"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048439047","display_name":"\u041erken Mamyrbayev","orcid":"https://orcid.org/0000-0001-8318-3794"},"institutions":[{"id":"https://openalex.org/I4210135055","display_name":"Institute of Information and Computational Technologies","ror":"https://ror.org/03v6e0k54","country_code":"KZ","type":"facility","lineage":["https://openalex.org/I4210135055"]}],"countries":["KZ"],"is_corresponding":false,"raw_author_name":"Orken Mamyrbayev","raw_affiliation_strings":["Institute of Information and Computational Technologies, Almaty 050010, Kazakhstan"],"raw_orcid":"https://orcid.org/0000-0001-8318-3794","affiliations":[{"raw_affiliation_string":"Institute of Information and Computational Technologies, Almaty 050010, Kazakhstan","institution_ids":["https://openalex.org/I4210135055"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017444954","display_name":"Kuralay Mukhsina","orcid":"https://orcid.org/0000-0002-8627-1949"},"institutions":[{"id":"https://openalex.org/I185571130","display_name":"Al-Farabi Kazakh National University","ror":"https://ror.org/03q0vrn42","country_code":"KZ","type":"education","lineage":["https://openalex.org/I185571130"]}],"countries":["KZ"],"is_corresponding":false,"raw_author_name":"Kuralay Mukhsina","raw_affiliation_strings":["Department of Informatics, Al-Farabi Kazakh National University, Almaty 050040, Kazakhstan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Informatics, Al-Farabi Kazakh National University, Almaty 050040, Kazakhstan","institution_ids":["https://openalex.org/I185571130"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5061829636","https://openalex.org/A5081869570"],"corresponding_institution_ids":["https://openalex.org/I67256668"],"apc_list":{"value":1600,"currency":"CHF","value_usd":1732},"apc_paid":{"value":1600,"currency":"CHF","value_usd":1732},"fwci":0.5077,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.75176381,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"3","issue":"4","first_page":"66","last_page":"66"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9994999766349792,"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"}},"topics":[{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9994999766349792,"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"}},{"id":"https://openalex.org/T12478","display_name":"Wikis in Education and Collaboration","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/3315","display_name":"Communication"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.987500011920929,"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":0.832733690738678},{"id":"https://openalex.org/keywords/wordnet","display_name":"WordNet","score":0.7453066110610962},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6722112894058228},{"id":"https://openalex.org/keywords/collocation","display_name":"Collocation (remote sensing)","score":0.6709085702896118},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.6064141988754272},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.588865339756012},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5429816246032715},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.5141499638557434},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.5083402991294861},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4956017732620239},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.4546920657157898},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.41320058703422546},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.11123600602149963}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.832733690738678},{"id":"https://openalex.org/C157659113","wikidata":"https://www.wikidata.org/wiki/Q533822","display_name":"WordNet","level":2,"score":0.7453066110610962},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6722112894058228},{"id":"https://openalex.org/C80023036","wikidata":"https://www.wikidata.org/wiki/Q5147531","display_name":"Collocation (remote sensing)","level":2,"score":0.6709085702896118},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.6064141988754272},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.588865339756012},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5429816246032715},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5141499638557434},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.5083402991294861},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4956017732620239},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.4546920657157898},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.41320058703422546},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.11123600602149963},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.3390/data3040066","is_oa":true,"landing_page_url":"https://doi.org/10.3390/data3040066","pdf_url":null,"source":{"id":"https://openalex.org/S4210226510","display_name":"Data","issn_l":"2306-5729","issn":["2306-5729"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Data","raw_type":"journal-article"},{"id":"pmh:oai:RePEc:gam:jdataj:v:3:y:2018:i:4:p:66-:d:190245","is_oa":false,"landing_page_url":"https://www.mdpi.com/2306-5729/3/4/66/","pdf_url":null,"source":{"id":"https://openalex.org/S4306401271","display_name":"RePEc: Research Papers in Economics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I77793887","host_organization_name":"Federal Reserve Bank of St. Louis","host_organization_lineage":["https://openalex.org/I77793887"],"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":"article"},{"id":"pmh:oai:doaj.org/article:7ca86828524048eab5bcbb593f20bc47","is_oa":true,"landing_page_url":"https://doaj.org/article/7ca86828524048eab5bcbb593f20bc47","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Data, Vol 3, Iss 4, p 66 (2018)","raw_type":"article"},{"id":"pmh:oai:mdpi.com:/2306-5729/3/4/66/","is_oa":true,"landing_page_url":"http://dx.doi.org/10.3390/data3040066","pdf_url":null,"source":{"id":"https://openalex.org/S4306400947","display_name":"MDPI (MDPI AG)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210097602","host_organization_name":"Multidisciplinary Digital Publishing Institute (Switzerland)","host_organization_lineage":["https://openalex.org/I4210097602"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Data","raw_type":"Text"},{"id":"pmh:oai:repository.kpi.kharkov.ua:KhPI-Press/46382","is_oa":false,"landing_page_url":"http://repository.kpi.kharkov.ua/handle/KhPI-Press/46382","pdf_url":null,"source":{"id":"https://openalex.org/S4306400269","display_name":"eNTUKhPIIR Repository (Kharkiv Polytechnic Institute)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67256668","host_organization_name":"National Technical University \"Kharkiv Polytechnic Institute\"","host_organization_lineage":["https://openalex.org/I67256668"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article"}],"best_oa_location":{"id":"doi:10.3390/data3040066","is_oa":true,"landing_page_url":"https://doi.org/10.3390/data3040066","pdf_url":null,"source":{"id":"https://openalex.org/S4210226510","display_name":"Data","issn_l":"2306-5729","issn":["2306-5729"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Data","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7300000190734863}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W17437045","https://openalex.org/W88325386","https://openalex.org/W167113224","https://openalex.org/W1952210680","https://openalex.org/W2061235289","https://openalex.org/W2100774734","https://openalex.org/W2126326820","https://openalex.org/W2138238299","https://openalex.org/W2252010905","https://openalex.org/W2264753273","https://openalex.org/W2346446020","https://openalex.org/W2353970688","https://openalex.org/W2778639274","https://openalex.org/W2892658594","https://openalex.org/W2895176335"],"related_works":["https://openalex.org/W2900382651","https://openalex.org/W1981879262","https://openalex.org/W2363417484","https://openalex.org/W4225863708","https://openalex.org/W1599970036","https://openalex.org/W1480103567","https://openalex.org/W158852162","https://openalex.org/W2331034580","https://openalex.org/W1984061923","https://openalex.org/W2152164004"],"abstract_inverted_index":{"Similar":[0],"text":[1,99],"fragments":[2,100],"extraction":[3],"from":[4,86],"weakly":[5],"formalized":[6],"data":[7,17],"is":[8,20],"the":[9,24,68,95],"task":[10],"of":[11,26,29,71,97,111,120],"natural":[12],"language":[13],"processing":[14],"and":[15,19,61,89],"intelligent":[16],"analysis":[18],"used":[21],"for":[22,53],"solving":[23],"problem":[25],"automatic":[27],"identification":[28],"connected":[30],"knowledge":[31],"fields.":[32],"In":[33],"order":[34],"to":[35,44],"search":[36],"such":[37],"common":[38,106,122],"communities":[39],"in":[40,101],"Wikipedia,":[41],"we":[42,66,77],"propose":[43],"use":[45],"as":[46],"an":[47,118],"additional":[48],"stage":[49],"a":[50],"logical-algebraic":[51],"model":[52],"similar":[54],"collocations":[55,115],"extraction.":[56],"With":[57,74],"Stanford":[58,62],"Part-Of-Speech":[59],"tagger":[60],"Universal":[63],"Dependencies":[64],"parser,":[65],"identify":[67],"grammatical":[69],"characteristics":[70],"collocation":[72],"words.":[73],"WordNet":[75],"synsets,":[76],"choose":[78],"their":[79],"synonyms.":[80],"Our":[81],"dataset":[82],"includes":[83],"Wikipedia":[84,102,124],"articles":[85,103],"different":[87],"portals":[88],"projects.":[90],"The":[91,109],"experimental":[92],"results":[93],"show":[94],"frequencies":[96],"synonymous":[98,114],"that":[104],"form":[105],"information":[107],"spaces.":[108],"number":[110],"highly":[112],"frequented":[113],"can":[116],"obtain":[117],"indication":[119],"key":[121],"up-to-date":[123],"communities.":[125]},"counts_by_year":[{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}
