{"id":"https://openalex.org/W7208825729","doi":"https://doi.org/10.5281/zenodo.22347374","title":"Uzbek Educational Text Corpus for TF\u2013IDF-Based Text Analysis","display_name":"Uzbek Educational Text Corpus for TF\u2013IDF-Based Text Analysis","publication_year":2026,"publication_date":"2026-09-05","ids":{"openalex":"https://openalex.org/W7208825729","doi":"https://doi.org/10.5281/zenodo.22347374"},"language":"uz","primary_location":{"id":"doi:10.5281/zenodo.22347374","doi":"https://doi.org/10.5281/zenodo.22347374","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.22347374","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dataset"},"volume":null,"type":"dataset","is_traditional":false,"indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.22347374","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5003849886","display_name":"Khabibulla A. Madatov","orcid":"https://orcid.org/0000-0002-3664-4954","observed_orcids":["https://orcid.org/0000-0002-3664-4954"]},"institutions":[{"id":"https://openalex.org/I14916453","display_name":"Urgench State University","ror":"https://ror.org/0593kfr97","country_code":"UZ","type":"education","lineage":["https://openalex.org/I14916453"]}],"countries":["UZ"],"is_corresponding":true,"raw_author_name":"Madatov, Khabibulla","raw_affiliation_strings":["Urgench State University"],"raw_orcid":"https://orcid.org/0000-0002-3664-4954","affiliations":[{"raw_affiliation_string":"Urgench State University","institution_ids":["https://openalex.org/I14916453"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5003849886"],"corresponding_institution_ids":["https://openalex.org/I14916453"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.3109999895095825,"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":0.3109999895095825,"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/T13910","display_name":"Computational and Text Analysis Methods","score":0.2992999851703644,"subfield":{"id":"https://openalex.org/subfields/3300","display_name":"General Social Sciences"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.2759000062942505,"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/uzbek-language","display_name":"Uzbek language","score":0.9940000176429749},{"id":"https://openalex.org/keywords/educational-texts","display_name":"educational texts","score":0.9829999804496765},{"id":"https://openalex.org/keywords/tf-idf","display_name":"TF-IDF","score":0.6740000247955322},{"id":"https://openalex.org/keywords/document-term-matrix","display_name":"term-document matrix","score":0.8730000257492065},{"id":"https://openalex.org/keywords/agglutinative-languages","display_name":"agglutinative languages","score":0.8769999742507935},{"id":"https://openalex.org/keywords/morphological-variation","display_name":"morphological variation","score":0.7580000162124634},{"id":"https://openalex.org/keywords/vocabulary-analysis","display_name":"vocabulary analysis","score":0.7239999771118164},{"id":"https://openalex.org/keywords/document-similarity","display_name":"document similarity","score":0.8820000290870667},{"id":"https://openalex.org/keywords/keyword-extraction","display_name":"keyword extraction","score":0.9470000267028809},{"id":"https://openalex.org/keywords/text-classification","display_name":"text classification","score":0.9549999833106995},{"id":"https://openalex.org/keywords/text-mining","display_name":"text mining","score":0.5910000205039978},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"information retrieval","score":0.800000011920929}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7416999936103821},{"id":"https://openalex.org/C2778718127","wikidata":"https://www.wikidata.org/wiki/Q9264","display_name":"Uzbek","level":2,"score":0.7324000000953674},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.7264000177383423},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6797000169754028},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6521000266075134},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.6011999845504761},{"id":"https://openalex.org/C2474386","wikidata":"https://www.wikidata.org/wiki/Q461183","display_name":"Text corpus","level":2,"score":0.49320000410079956},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.460099995136261},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.43950000405311584},{"id":"https://openalex.org/C532629269","wikidata":"https://www.wikidata.org/wiki/Q865083","display_name":"Corpus linguistics","level":2,"score":0.42500001192092896},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4047999978065491},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.3953999876976013},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.37689998745918274},{"id":"https://openalex.org/C3018949938","wikidata":"https://www.wikidata.org/wiki/Q17166101","display_name":"Text messaging","level":2,"score":0.33880001306533813},{"id":"https://openalex.org/C2986587452","wikidata":"https://www.wikidata.org/wiki/Q938438","display_name":"Statistical analysis","level":2,"score":0.33739998936653137},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.32359999418258667},{"id":"https://openalex.org/C10551718","wikidata":"https://www.wikidata.org/wiki/Q5227332","display_name":"Data pre-processing","level":2,"score":0.32120001316070557},{"id":"https://openalex.org/C2779500292","wikidata":"https://www.wikidata.org/wiki/Q14802672","display_name":"Text processing","level":2,"score":0.3197000026702881},{"id":"https://openalex.org/C2776092919","wikidata":"https://www.wikidata.org/wiki/Q9072","display_name":"Estonian","level":2,"score":0.2939999997615814},{"id":"https://openalex.org/C110615152","wikidata":"https://www.wikidata.org/wiki/Q1469824","display_name":"Controlled vocabulary","level":2,"score":0.2827000021934509},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.2818000018596649},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.273499995470047},{"id":"https://openalex.org/C58642233","wikidata":"https://www.wikidata.org/wiki/Q8269924","display_name":"Taxonomy (biology)","level":2,"score":0.26269999146461487}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5281/zenodo.22347374","doi":"https://doi.org/10.5281/zenodo.22347374","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.22347374","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dataset"},{"id":"doi:10.5281/zenodo.22347375","doi":"https://doi.org/10.5281/zenodo.22347375","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.22347375","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dataset"}],"best_oa_location":{"id":"doi:10.5281/zenodo.22347374","doi":"https://doi.org/10.5281/zenodo.22347374","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.22347374","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dataset"},"sustainable_development_goals":[{"score":0.6164000034332275,"display_name":"Quality education","id":"https://metadata.un.org/sdg/4"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W6911877431","https://openalex.org/W4414968565","https://openalex.org/W7159623878","https://openalex.org/W4410735829","https://openalex.org/W7171811326","https://openalex.org/W4393705657","https://openalex.org/W7203621887","https://openalex.org/W7204905356","https://openalex.org/W7167288047","https://openalex.org/W7165187812"],"abstract_inverted_index":{"This":[0],"dataset":[1,89,172],"contains":[2],"a":[3],"corpus":[4,38],"of":[5,57,96,117,156,167,185],"132":[6,170],"Uzbek-language":[7],"educational":[8,58],"texts":[9,20],"collected":[10],"and":[11,15,27,35,54,82,85,114,129,134,180],"prepared":[12,174],"for":[13,66,175,182],"computational":[14],"statistical":[16,84],"text":[17,52,80,168],"analysis.":[18],"The":[19,37,88,119,171],"are":[21,121],"stored":[22],"in":[23,123],"plain":[24],"TXT":[25],"format":[26,125],"organized":[28],"into":[29],"four":[30],"archives:":[31],"TXT_bolimlar1,":[32],"TXT_bolimlar2,":[33],"TXT_bolimlar3,":[34],"darslik.":[36],"is":[39,90],"intended":[40],"to":[41,93,126],"support":[42],"research":[43,176],"on":[44,153,177,191],"Uzbek":[45,97,186],"natural":[46],"language":[47],"processing":[48],"(NLP),":[49],"information":[50],"retrieval,":[51],"mining,":[53],"quantitative":[55],"analysis":[56,184],"texts.":[59],"In":[60],"particular,":[61],"it":[62],"can":[63,105],"be":[64],"used":[65],"experiments":[67],"involving":[68],"TF\u2013IDF":[69],"weighting,":[70],"term\u2013document":[71],"matrix":[72],"construction,":[73],"vocabulary":[74,108],"analysis,":[75],"document":[76],"similarity,":[77],"keyword":[78],"extraction,":[79],"classification,":[81],"related":[83],"machine-learning":[86],"methods.":[87,193],"particularly":[91],"relevant":[92],"the":[94,154],"study":[95],"as":[98],"an":[99],"agglutinative":[100],"language,":[101],"where":[102],"morphological":[103],"variation":[104],"significantly":[106],"affect":[107],"size,":[109],"term":[110],"frequency":[111],"distributions,":[112],"sparsity,":[113],"vector-space":[115],"representations":[116],"documents.":[118],"files":[120],"provided":[122],"plain-text":[124],"facilitate":[127],"preprocessing":[128,150],"integration":[130],"with":[131,188],"common":[132],"NLP":[133],"data-analysis":[135],"tools.":[136],"Researchers":[137],"may":[138],"apply":[139],"their":[140,157],"own":[141],"tokenization,":[142],"normalization,":[143],"stop-word":[144],"removal,":[145],"stemming,":[146],"lemmatization,":[147],"or":[148],"other":[149],"procedures":[151],"depending":[152],"objectives":[155],"experiments.":[158],"Dataset":[159],"contents:":[160],"TXT_bolimlar1.zip":[161],"TXT_bolimlar2.zip":[162],"TXT_bolimlar3.zip":[163],"darslik.zip":[164],"Total":[165],"number":[166],"documents:":[169],"was":[173],"mathematical":[178],"models":[179],"algorithms":[181],"intelligent":[183],"texts,":[187],"particular":[189],"emphasis":[190],"TF\u2013IDF-based":[192]},"counts_by_year":[],"updated_date":"2026-10-08T09:06:37.294493","created_date":"2026-09-06T00:00:00"}