{"id":"https://openalex.org/W2614255939","doi":"https://doi.org/10.4149/cai_2017_1_186","title":"Experiment on Methods for Clustering and Categorization of Polish Text","display_name":"Experiment on Methods for Clustering and Categorization of Polish Text","publication_year":2017,"publication_date":"2017-01-01","ids":{"openalex":"https://openalex.org/W2614255939","doi":"https://doi.org/10.4149/cai_2017_1_186","mag":"2614255939"},"language":"en","primary_location":{"id":"doi:10.4149/cai_2017_1_186","is_oa":true,"landing_page_url":"https://doi.org/10.4149/cai_2017_1_186","pdf_url":null,"source":{"id":"https://openalex.org/S4210200093","display_name":"Computing and Informatics","issn_l":"1335-9150","issn":["1335-9150","2585-8807"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computing and Informatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.4149/cai_2017_1_186","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5045630744","display_name":"Maciej Wielgosz","orcid":"https://orcid.org/0000-0002-4401-2957"},"institutions":[{"id":"https://openalex.org/I686019","display_name":"AGH University of Krakow","ror":"https://ror.org/00bas1c41","country_code":"PL","type":"education","lineage":["https://openalex.org/I686019"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Maciej Wielgosz","raw_affiliation_strings":["AGH University of Science and Technology, Cracow"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AGH University of Science and Technology, Cracow","institution_ids":["https://openalex.org/I686019"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089339623","display_name":"Rafa\u0142 Fr\u0105czek","orcid":"https://orcid.org/0000-0002-4311-2083"},"institutions":[{"id":"https://openalex.org/I686019","display_name":"AGH University of Krakow","ror":"https://ror.org/00bas1c41","country_code":"PL","type":"education","lineage":["https://openalex.org/I686019"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Rafa\u0142 Fraczek","raw_affiliation_strings":["AGH University of Science and Technology, Cracow"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AGH University of Science and Technology, Cracow","institution_ids":["https://openalex.org/I686019"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052669287","display_name":"Pawel Grzegorz Russek","orcid":"https://orcid.org/0000-0003-3858-4278"},"institutions":[{"id":"https://openalex.org/I686019","display_name":"AGH University of Krakow","ror":"https://ror.org/00bas1c41","country_code":"PL","type":"education","lineage":["https://openalex.org/I686019"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Pawe\u0142 Russek","raw_affiliation_strings":["AGH University of Science and Technology, Cracow"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AGH University of Science and Technology, Cracow","institution_ids":["https://openalex.org/I686019"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036847074","display_name":"Marcin Pietro\u0144","orcid":"https://orcid.org/0000-0001-9357-9231"},"institutions":[{"id":"https://openalex.org/I686019","display_name":"AGH University of Krakow","ror":"https://ror.org/00bas1c41","country_code":"PL","type":"education","lineage":["https://openalex.org/I686019"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Marcin Pietro\u0144","raw_affiliation_strings":["AGH University of Science and Technology, Cracow"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AGH University of Science and Technology, Cracow","institution_ids":["https://openalex.org/I686019"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048867017","display_name":"Agnieszka D\u0105browska-Boruch","orcid":"https://orcid.org/0000-0003-2900-5668"},"institutions":[{"id":"https://openalex.org/I686019","display_name":"AGH University of Krakow","ror":"https://ror.org/00bas1c41","country_code":"PL","type":"education","lineage":["https://openalex.org/I686019"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Agnieszka Dabrowska-Boruch","raw_affiliation_strings":["AGH University of Science and Technology, Cracow"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AGH University of Science and Technology, Cracow","institution_ids":["https://openalex.org/I686019"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082630408","display_name":"E. Jamro","orcid":"https://orcid.org/0000-0003-4632-2470"},"institutions":[{"id":"https://openalex.org/I686019","display_name":"AGH University of Krakow","ror":"https://ror.org/00bas1c41","country_code":"PL","type":"education","lineage":["https://openalex.org/I686019"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Ernest Jamro","raw_affiliation_strings":["AGH University of Science and Technology, Cracow"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AGH University of Science and Technology, Cracow","institution_ids":["https://openalex.org/I686019"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048697784","display_name":"K. Wiatr","orcid":"https://orcid.org/0000-0001-5959-0277"},"institutions":[{"id":"https://openalex.org/I686019","display_name":"AGH University of Krakow","ror":"https://ror.org/00bas1c41","country_code":"PL","type":"education","lineage":["https://openalex.org/I686019"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Kazimierz Wiatr","raw_affiliation_strings":["AGH University of Science and Technology, Cracow"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AGH University of Science and Technology, Cracow","institution_ids":["https://openalex.org/I686019"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.04675824,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"36","issue":"1","first_page":"186","last_page":"204"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.989300012588501,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.989300012588501,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9883999824523926,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9850000143051147,"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/cluster-analysis","display_name":"Cluster analysis","score":0.8239128589630127},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.807320237159729},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7619755268096924},{"id":"https://openalex.org/keywords/tf\u2013idf","display_name":"tf\u2013idf","score":0.6943579316139221},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6052477359771729},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.5405498743057251},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5188504457473755},{"id":"https://openalex.org/keywords/vector-space-model","display_name":"Vector space model","score":0.4727172255516052},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4615497589111328},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4563009440898895},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.39348018169403076},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3694359362125397},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3505364656448364},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07454994320869446}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.8239128589630127},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.807320237159729},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7619755268096924},{"id":"https://openalex.org/C81758059","wikidata":"https://www.wikidata.org/wiki/Q796584","display_name":"tf\u2013idf","level":3,"score":0.6943579316139221},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6052477359771729},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.5405498743057251},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5188504457473755},{"id":"https://openalex.org/C89686163","wikidata":"https://www.wikidata.org/wiki/Q1187982","display_name":"Vector space model","level":2,"score":0.4727172255516052},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4615497589111328},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4563009440898895},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.39348018169403076},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3694359362125397},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3505364656448364},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07454994320869446},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.4149/cai_2017_1_186","is_oa":true,"landing_page_url":"https://doi.org/10.4149/cai_2017_1_186","pdf_url":null,"source":{"id":"https://openalex.org/S4210200093","display_name":"Computing and Informatics","issn_l":"1335-9150","issn":["1335-9150","2585-8807"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computing and Informatics","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.4149/cai_2017_1_186","is_oa":true,"landing_page_url":"https://doi.org/10.4149/cai_2017_1_186","pdf_url":null,"source":{"id":"https://openalex.org/S4210200093","display_name":"Computing and Informatics","issn_l":"1335-9150","issn":["1335-9150","2585-8807"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computing and Informatics","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7400000095367432,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W168564468","https://openalex.org/W1494792294","https://openalex.org/W1584259869","https://openalex.org/W1893362560","https://openalex.org/W2073992149","https://openalex.org/W2085256060","https://openalex.org/W2118027802","https://openalex.org/W2149684865","https://openalex.org/W2152525996","https://openalex.org/W2165612380","https://openalex.org/W2344069985"],"related_works":["https://openalex.org/W2549551998","https://openalex.org/W3036265557","https://openalex.org/W2900987978","https://openalex.org/W2975262101","https://openalex.org/W2163957714","https://openalex.org/W3109760095","https://openalex.org/W3150575538","https://openalex.org/W2365583997","https://openalex.org/W2611384481","https://openalex.org/W3028990185"],"abstract_inverted_index":{"The":[0,50,60,82,112],"main":[1],"goal":[2],"of":[3,16,37,47,99,107,114,125,145],"this":[4],"work":[5],"was":[6,26,41,52,63,72,116],"to":[7,79,121,141],"experimentally":[8],"verify":[9],"the":[10,30,38,44,55,66,126,129,133,137,143],"methods":[11,40],"for":[12,29,43],"a":[13],"challenging":[14],"task":[15],"categorization":[17,31,134],"and":[18,23,32,90,109,135],"clustering":[19],"Polish":[20,48],"text.":[21],"Supervised":[22],"unsupervised":[24],"learning":[25],"employed":[27,39],"respectively":[28],"clustering.":[33],"A":[34],"profound":[35],"examination":[36],"done":[42],"custom-built":[45],"corpus":[46,51,61],"texts.":[49],"assembled":[53],"by":[54,74,76,128],"authors":[56,138],"from":[57,65],"Internet":[58],"resources.":[59],"data":[62],"acquired":[64],"news":[67],"portal":[68],"and,":[69],"therefore,":[70],"it":[71],"sorted":[73],"type":[75],"journalists":[77],"according":[78],"their":[80,110,119],"specialization.":[81],"presented":[83],"algorithms":[84,108,115],"employ":[85],"Vector":[86],"Space":[87],"Model":[88],"(VSM)":[89],"TF-IDF":[91],"(Term":[92],"Frequency-Inverse":[93],"Document":[94],"Frequency)":[95],"weighing":[96],"scheme.":[97],"Series":[98],"experiments":[100],"were":[101],"conducted":[102],"that":[103],"revealed":[104],"certain":[105],"properties":[106],"accuracy.":[111],"accuracy":[113],"elaborated":[117],"regarding":[118],"ability":[120],"match":[122],"human":[123],"arrangement":[124],"documents":[127],"topic.":[130],"For":[131],"both":[132],"clustering,":[136],"used":[139],"F-measure":[140],"assess":[142],"quality":[144],"allocation.":[146]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
