{"id":"https://openalex.org/W7225640615","doi":"https://doi.org/10.21869/2223-1536-2026-16-3-8-21","title":"Text data preprocessing module in an intelligent classification system","display_name":"Text data preprocessing module in an intelligent classification system","publication_year":2026,"publication_date":"2026-11-08","ids":{"openalex":"https://openalex.org/W7225640615","doi":"https://doi.org/10.21869/2223-1536-2026-16-3-8-21"},"language":"en","primary_location":{"id":"doi:10.21869/2223-1536-2026-16-3-8-21","doi":"https://doi.org/10.21869/2223-1536-2026-16-3-8-21","is_oa":true,"landing_page_url":"https://doi.org/10.21869/2223-1536-2026-16-3-8-21","pdf_url":"https://uprinmatus.elpub.ru/jour/article/download/529/274","source":{"id":"https://openalex.org/S4387289768","display_name":"Proceedings of the Southwest State University Series IT Management Computer Science Computer Engineering Medical Equipment Engineering","issn_l":"2223-1536","issn":["2223-1536"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["russia-white-list-3"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Southwest State University. Series: IT Management, Computer Science, Computer Engineering. Medical Equipment Engineering","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://uprinmatus.elpub.ru/jour/article/download/529/274","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5114662734","display_name":"Zh. T. Zhusubaliyev","orcid":"https://orcid.org/0009-0009-3117-5595","observed_orcids":["https://orcid.org/0009-0009-3117-5595"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"S. V. Efanov","raw_affiliation_strings":["Southwest State University"],"raw_orcid":"https://orcid.org/0009-0009-3117-5595","affiliations":[{"raw_affiliation_string":"Southwest State University","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102490368","display_name":"Elena Nikitichna Ivanova","orcid":"https://orcid.org/0009-0003-4466-5928","observed_orcids":["https://orcid.org/0009-0003-4466-5928"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"E. N. Ivanova","raw_affiliation_strings":["Southwest State University"],"raw_orcid":"https://orcid.org/0009-0003-4466-5928","affiliations":[{"raw_affiliation_string":"Southwest State University","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057438577","display_name":"Irina Evgenyevna Chernetskaya","orcid":"https://orcid.org/0009-0009-8254-9606","observed_orcids":["https://orcid.org/0009-0009-8254-9606"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"I. E. Chernetskaya","raw_affiliation_strings":["Southwest State University"],"raw_orcid":"https://orcid.org/0009-0009-8254-9606","affiliations":[{"raw_affiliation_string":"Southwest State University","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"16","issue":"3","first_page":"8","last_page":"21"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.8105000257492065,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.8105000257492065,"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":0.13660000264644623,"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/T10028","display_name":"Topic Modeling","score":0.02290000021457672,"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/text-preprocessing","display_name":"text preprocessing","score":0.8240000009536743},{"id":"https://openalex.org/keywords/document-parsing","display_name":"document parsing","score":0.8320000171661377},{"id":"https://openalex.org/keywords/tokenization","display_name":"tokenization","score":0.9879999756813049},{"id":"https://openalex.org/keywords/character-frequency-analysis","display_name":"character frequency analysis","score":0.8080000281333923},{"id":"https://openalex.org/keywords/multilingual-text","display_name":"multilingual text","score":0.7429999709129333},{"id":"https://openalex.org/keywords/corrupted-data","display_name":"corrupted data","score":0.6919999718666077},{"id":"https://openalex.org/keywords/feature-space-construction","display_name":"feature space construction","score":0.9049999713897705}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8349999785423279},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.6104000210762024},{"id":"https://openalex.org/C176982825","wikidata":"https://www.wikidata.org/wiki/Q835922","display_name":"Lexical analysis","level":2,"score":0.6011000275611877},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.5773000121116638},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5541999936103821},{"id":"https://openalex.org/C2779500292","wikidata":"https://www.wikidata.org/wiki/Q14802672","display_name":"Text processing","level":2,"score":0.5485000014305115},{"id":"https://openalex.org/C10551718","wikidata":"https://www.wikidata.org/wiki/Q5227332","display_name":"Data pre-processing","level":2,"score":0.4966000020503998},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.446399986743927},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.42160001397132874},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.3944000005722046},{"id":"https://openalex.org/C138827492","wikidata":"https://www.wikidata.org/wiki/Q6661985","display_name":"Data processing","level":2,"score":0.3903000056743622},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.38440001010894775},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.3684999942779541},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.34540000557899475},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.336899995803833},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.334199994802475},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.31679999828338623},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.3077000081539154},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.304500013589859},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.2994000017642975},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.29350000619888306},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.27889999747276306},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.27549999952316284},{"id":"https://openalex.org/C87868495","wikidata":"https://www.wikidata.org/wiki/Q750843","display_name":"Information processing","level":2,"score":0.2736000120639801},{"id":"https://openalex.org/C2778330532","wikidata":"https://www.wikidata.org/wiki/Q4826577","display_name":"Automatic indexing","level":3,"score":0.2734000086784363},{"id":"https://openalex.org/C115901376","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automation","level":2,"score":0.2680000066757202},{"id":"https://openalex.org/C2778012447","wikidata":"https://www.wikidata.org/wiki/Q1034415","display_name":"Scope (computer science)","level":2,"score":0.2621000111103058},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.25940001010894775},{"id":"https://openalex.org/C188338183","wikidata":"https://www.wikidata.org/wiki/Q80735","display_name":"Stop words","level":3,"score":0.2524999976158142},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.25040000677108765}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21869/2223-1536-2026-16-3-8-21","doi":"https://doi.org/10.21869/2223-1536-2026-16-3-8-21","is_oa":true,"landing_page_url":"https://doi.org/10.21869/2223-1536-2026-16-3-8-21","pdf_url":"https://uprinmatus.elpub.ru/jour/article/download/529/274","source":{"id":"https://openalex.org/S4387289768","display_name":"Proceedings of the Southwest State University Series IT Management Computer Science Computer Engineering Medical Equipment Engineering","issn_l":"2223-1536","issn":["2223-1536"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["russia-white-list-3"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Southwest State University. Series: IT Management, Computer Science, Computer Engineering. Medical Equipment Engineering","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.21869/2223-1536-2026-16-3-8-21","doi":"https://doi.org/10.21869/2223-1536-2026-16-3-8-21","is_oa":true,"landing_page_url":"https://doi.org/10.21869/2223-1536-2026-16-3-8-21","pdf_url":"https://uprinmatus.elpub.ru/jour/article/download/529/274","source":{"id":"https://openalex.org/S4387289768","display_name":"Proceedings of the Southwest State University Series IT Management Computer Science Computer Engineering Medical Equipment Engineering","issn_l":"2223-1536","issn":["2223-1536"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["russia-white-list-3"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Southwest State University. Series: IT Management, Computer Science, Computer Engineering. Medical Equipment Engineering","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7225640615.pdf","grobid_xml":"https://content.openalex.org/works/W7225640615.grobid-xml"},"referenced_works_count":16,"referenced_works":["https://openalex.org/W4295222521","https://openalex.org/W4387622895","https://openalex.org/W4391275741","https://openalex.org/W4401547013","https://openalex.org/W4403138231","https://openalex.org/W4403138264","https://openalex.org/W4404419720","https://openalex.org/W4405542150","https://openalex.org/W4405542227","https://openalex.org/W4406397437","https://openalex.org/W4412089450","https://openalex.org/W4413954908","https://openalex.org/W4413954940","https://openalex.org/W4415246901","https://openalex.org/W7136542420","https://openalex.org/W7143501851"],"related_works":["https://openalex.org/W2189266921","https://openalex.org/W3195119315","https://openalex.org/W4404419720","https://openalex.org/W2128254788","https://openalex.org/W2921966207","https://openalex.org/W3186812997","https://openalex.org/W2904689355","https://openalex.org/W2323985126","https://openalex.org/W2896608996","https://openalex.org/W2014545475"],"abstract_inverted_index":{"Purpose":[0],"of":[1,5,16,38,59,71,87,120,156,167,187,196,210,214,220,246,259],"research.":[2],"The":[3,30,234],"purpose":[4],"this":[6,60],"study":[7],"is":[8,33,64,165],"to":[9,65,117,142,203,256],"develop":[10],"and":[11,48,68,103,181,206,244,251],"conduct":[12],"a":[13,17,154,160],"comprehensive":[14],"analysis":[15,130,258],"text":[18,89,101],"data":[19,73],"preprocessing":[20,236],"module":[21,161,199,237],"intended":[22],"for":[23,98,124],"use":[24,119,195],"within":[25],"an":[26,121,144],"intelligent":[27,88,248],"classification":[28,201,249],"system.":[29],"primary":[31],"focus":[32],"on":[34,149],"improving":[35],"the":[36,57,62,82,118,157,185,194,197,218,221,242,247,257],"quality":[37],"processing":[39,70,90,209],"complex":[40,176],"textual":[41,150,170,260],"information,":[42],"which":[43,138],"may":[44,49],"be":[45,253],"unstructured,":[46],"multilingual,":[47],"also":[50],"contain":[51],"errors":[52],"or":[53],"partial":[54],"corruption.":[55],"Within":[56],"scope":[58],"work,":[61],"task":[63],"ensure":[66],"stable":[67,208],"efficient":[69],"such":[72,178],"under":[74],"real-world":[75],"information":[76,171,261],"flow":[77],"conditions.":[78],"Methods.":[79],"To":[80],"achieve":[81],"stated":[83],"objective,":[84],"modern":[85],"methods":[86,131],"were":[91,111,132],"employed.":[92],"In":[93],"particular,":[94],"document":[95],"parsing":[96],"algorithms":[97],"various":[99,173],"formats,":[100],"cleaning":[102],"normalization":[104],"procedures,":[105],"as":[106,108,179],"well":[107],"tokenization":[109],"techniques":[110],"applied.":[112],"Special":[113],"attention":[114],"was":[115,162],"given":[116],"n-gram":[122,222],"approach":[123],"automatic":[125],"language":[126,229],"detection.":[127],"Additionally,":[128],"statistical":[129],"utilized,":[133],"including":[134,175],"character":[135],"frequency":[136],"analysis,":[137],"made":[139],"it":[140],"possible":[141],"construct":[143],"informative":[145],"feature":[146],"space":[147],"based":[148],"representations.":[151],"Results.":[152],"As":[153],"result":[155],"conducted":[158],"research,":[159],"developed":[163,235],"that":[164,193],"capable":[166],"efficiently":[168],"extracting":[169],"from":[172],"sources,":[174],"formats":[177],"JSON":[180],"XML,":[182],"even":[183],"in":[184,228,262],"presence":[186],"corrupted":[188],"data.":[189,216],"Experimental":[190],"evaluation":[191],"demonstrated":[192],"proposed":[198],"increases":[200],"accuracy":[202,227],"approximately":[204],"89%":[205],"ensures":[207],"more":[211],"than":[212],"90%":[213],"input":[215],"Furthermore,":[217],"application":[219],"algorithm":[223],"enabled":[224],"achieving":[225],"high":[226,239],"detection,":[230],"exceeding":[231],"91%.":[232],"Conclusion.":[233],"demonstrates":[238],"efficiency,":[240],"enhances":[241],"reliability":[243],"versatility":[245],"system,":[250],"can":[252],"successfully":[254],"applied":[255],"practical":[263],"tasks.":[264]},"counts_by_year":[],"updated_date":"2026-11-11T12:16:26.678958","created_date":"2026-11-10T00:00:00"}