{"id":"https://openalex.org/W4413089936","doi":"https://doi.org/10.53894/ijirss.v8i4.8356","title":"Document analysis via combined vectorization and machine learning approaches","display_name":"Document analysis via combined vectorization and machine learning approaches","publication_year":2025,"publication_date":"2025-07-07","ids":{"openalex":"https://openalex.org/W4413089936","doi":"https://doi.org/10.53894/ijirss.v8i4.8356"},"language":"en","primary_location":{"id":"doi:10.53894/ijirss.v8i4.8356","doi":"https://doi.org/10.53894/ijirss.v8i4.8356","is_oa":true,"landing_page_url":"https://doi.org/10.53894/ijirss.v8i4.8356","pdf_url":"http://www.ijirss.com/index.php/ijirss/article/download/8356/1874","source":{"id":"https://openalex.org/S4210240683","display_name":"International Journal of Innovative Research and Scientific Studies","issn_l":"2617-6548","issn":["2617-6548","2790-7600"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":["anvur-scientific","poland-20","russia-white-list-3"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Innovative Research and Scientific Studies","raw_type":"journal-article"},"volume":null,"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"http://www.ijirss.com/index.php/ijirss/article/download/8356/1874","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5065672511","display_name":"Dinara Kaibassova","orcid":"https://orcid.org/0000-0002-8410-7758","observed_orcids":["https://orcid.org/0000-0002-8410-7758"]},"institutions":[{"id":"https://openalex.org/I4405257690","display_name":"Astana IT University","ror":"https://ror.org/05jnvbc31","country_code":"KZ","type":"education","lineage":["https://openalex.org/I4405257690"]}],"countries":["KZ"],"is_corresponding":false,"raw_author_name":"Dinara Kaibassova","raw_affiliation_strings":["Astana IT University, Astana, 010000, Kazakhstan"],"raw_orcid":"https://orcid.org/0000-0002-8410-7758","affiliations":[{"raw_affiliation_string":"Astana IT University, Astana, 010000, Kazakhstan","institution_ids":["https://openalex.org/I4405257690"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040461401","display_name":"Bigul MUKHAMETZHANOVA","orcid":"https://orcid.org/0000-0003-3585-8181","observed_orcids":["https://orcid.org/0000-0003-3585-8181"]},"institutions":[{"id":"https://openalex.org/I4210131705","display_name":"Abylkas Saginov Karaganda Technical University","ror":"https://ror.org/03x368n87","country_code":"KZ","type":"education","lineage":["https://openalex.org/I4210131705"]}],"countries":["KZ"],"is_corresponding":false,"raw_author_name":"Bigul Mukhametzhanova","raw_affiliation_strings":["Abylkas Saginov Karaganda Technical University, Karaganda, 100000, Kazakhstan"],"raw_orcid":"https://orcid.org/0000-0003-3585-8181","affiliations":[{"raw_affiliation_string":"Abylkas Saginov Karaganda Technical University, Karaganda, 100000, Kazakhstan","institution_ids":["https://openalex.org/I4210131705"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044599771","display_name":"Dinara TOKSEIT","orcid":"https://orcid.org/0000-0001-9075-3943","observed_orcids":["https://orcid.org/0000-0001-9075-3943"]},"institutions":[{"id":"https://openalex.org/I10232997","display_name":"L. N. Gumilyov Eurasian National University","ror":"https://ror.org/0242cby63","country_code":"KZ","type":"education","lineage":["https://openalex.org/I10232997"]}],"countries":["KZ"],"is_corresponding":false,"raw_author_name":"Dinara Tokseit","raw_affiliation_strings":["L. N. Gumilyov Eurasian National University, Astana, 010000, Kazakhstan"],"raw_orcid":"https://orcid.org/0000-0001-9075-3943","affiliations":[{"raw_affiliation_string":"L. N. Gumilyov Eurasian National University, Astana, 010000, Kazakhstan","institution_ids":["https://openalex.org/I10232997"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086158683","display_name":"Aigul Kubegenova","orcid":"https://orcid.org/0000-0003-0156-7757","observed_orcids":["https://orcid.org/0000-0003-0156-7757"]},"institutions":[{"id":"https://openalex.org/I4210136233","display_name":"Zhangir Khan West Kazakhstan Agrarian Technical University","ror":"https://ror.org/03h8f2y52","country_code":"KZ","type":"education","lineage":["https://openalex.org/I4210136233"]}],"countries":["KZ"],"is_corresponding":false,"raw_author_name":"Aigul Kubegenova","raw_affiliation_strings":["West Kazakhstan Agrarian and Technical University named after Zhangir Khan, Uralsk, 090000, Kazakhstan"],"raw_orcid":"https://orcid.org/0000-0003-0156-7757","affiliations":[{"raw_affiliation_string":"West Kazakhstan Agrarian and Technical University named after Zhangir Khan, Uralsk, 090000, Kazakhstan","institution_ids":["https://openalex.org/I4210136233"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001741776","display_name":"Murat G. Kozhanov","orcid":"https://orcid.org/0000-0002-5310-9953","observed_orcids":["https://orcid.org/0000-0002-5310-9953"]},"institutions":[{"id":"https://openalex.org/I4210131705","display_name":"Abylkas Saginov Karaganda Technical University","ror":"https://ror.org/03x368n87","country_code":"KZ","type":"education","lineage":["https://openalex.org/I4210131705"]}],"countries":["KZ"],"is_corresponding":false,"raw_author_name":"Murad Kozhanov","raw_affiliation_strings":["Abylkas Saginov Karaganda Technical University, Karaganda, 100000, Kazakhstan"],"raw_orcid":"https://orcid.org/0000-0002-5310-9953","affiliations":[{"raw_affiliation_string":"Abylkas Saginov Karaganda Technical University, Karaganda, 100000, Kazakhstan","institution_ids":["https://openalex.org/I4210131705"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4011,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.63597915,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":96},"biblio":{"volume":"8","issue":"4","first_page":"2195","last_page":"2204"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9965999722480774,"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":0.9965999722480774,"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":0.003000000026077032,"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":9.999999747378752e-05,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/automatic-document-classification","display_name":"automatic document classification","score":0.9480000138282776},{"id":"https://openalex.org/keywords/tf-idf","display_name":"TF-IDF","score":0.968999981880188},{"id":"https://openalex.org/keywords/word2vec-embeddings","display_name":"Word2Vec embeddings","score":0.8980000019073486},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"support vector machine","score":0.8109999895095825},{"id":"https://openalex.org/keywords/random-forest","display_name":"random forest","score":0.9980000257492065},{"id":"https://openalex.org/keywords/semantic-text-representation","display_name":"semantic text representation","score":0.8560000061988831},{"id":"https://openalex.org/keywords/text-preprocessing","display_name":"text preprocessing","score":0.7170000076293945},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"feature extraction","score":0.7300000190734863},{"id":"https://openalex.org/keywords/document-analysis","display_name":"document analysis","score":0.6050000190734863}],"concepts":[{"id":"https://openalex.org/C2776461190","wikidata":"https://www.wikidata.org/wiki/Q22673982","display_name":"Word2vec","level":3,"score":0.8267233967781067},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8093623518943787},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7290460467338562},{"id":"https://openalex.org/C81758059","wikidata":"https://www.wikidata.org/wiki/Q796584","display_name":"tf\u2013idf","level":3,"score":0.647705078125},{"id":"https://openalex.org/C41681595","wikidata":"https://www.wikidata.org/wiki/Q7917855","display_name":"Vectorization (mathematics)","level":2,"score":0.6335207223892212},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.6287173628807068},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5521336197853088},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.5409733653068542},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4730602502822876},{"id":"https://openalex.org/C66402592","wikidata":"https://www.wikidata.org/wiki/Q2271421","display_name":"Sentiment analysis","level":2,"score":0.4704053997993469},{"id":"https://openalex.org/C176982825","wikidata":"https://www.wikidata.org/wiki/Q835922","display_name":"Lexical analysis","level":2,"score":0.4492468237876892},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3960891664028168},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.13781017065048218},{"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/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.53894/ijirss.v8i4.8356","doi":"https://doi.org/10.53894/ijirss.v8i4.8356","is_oa":true,"landing_page_url":"https://doi.org/10.53894/ijirss.v8i4.8356","pdf_url":"http://www.ijirss.com/index.php/ijirss/article/download/8356/1874","source":{"id":"https://openalex.org/S4210240683","display_name":"International Journal of Innovative Research and Scientific Studies","issn_l":"2617-6548","issn":["2617-6548","2790-7600"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":["anvur-scientific","poland-20","russia-white-list-3"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Innovative Research and Scientific Studies","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.53894/ijirss.v8i4.8356","doi":"https://doi.org/10.53894/ijirss.v8i4.8356","is_oa":true,"landing_page_url":"https://doi.org/10.53894/ijirss.v8i4.8356","pdf_url":"http://www.ijirss.com/index.php/ijirss/article/download/8356/1874","source":{"id":"https://openalex.org/S4210240683","display_name":"International Journal of Innovative Research and Scientific Studies","issn_l":"2617-6548","issn":["2617-6548","2790-7600"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":["anvur-scientific","poland-20","russia-white-list-3"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Innovative Research and Scientific Studies","raw_type":"journal-article"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality education","score":0.7400000095367432}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4413089936.pdf","grobid_xml":"https://content.openalex.org/works/W4413089936.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4409430504","https://openalex.org/W2956864576","https://openalex.org/W2359191301","https://openalex.org/W2062522089","https://openalex.org/W4393035576","https://openalex.org/W229811353","https://openalex.org/W2997521053","https://openalex.org/W2580878117","https://openalex.org/W2958550837","https://openalex.org/W2530676541"],"abstract_inverted_index":{"The":[0,28,50,114],"purpose":[1],"of":[2,101,107,133],"this":[3],"study":[4,115],"is":[5],"to":[6,169],"develop":[7],"an":[8,99],"effective":[9],"hybrid":[10,118],"model":[11,65,91],"for":[12,149,162],"automatic":[13],"document":[14,134],"classification":[15,70,148],"by":[16],"combining":[17,120],"statistical":[18],"and":[19,36,47,61,67,80,98,122,131,151,154],"semantic":[20,109],"text":[21,147,165],"vectorization":[22],"techniques":[23],"with":[24,39,124],"machine":[25],"learning":[26],"algorithms.":[27],"methodology":[29],"integrates":[30],"Term":[31],"Frequency\u2013Inverse":[32],"Document":[33],"Frequency":[34],"(TF-IDF)":[35],"Word2Vec":[37,88,123],"embeddings":[38],"classifiers":[40,126],"such":[41,72],"as":[42,73],"Support":[43],"Vector":[44],"Machine":[45],"(SVM)":[46],"Random":[48],"Forest.":[49],"proposed":[51],"approach":[52],"includes":[53],"data":[54],"preprocessing":[55],"(tokenization,":[56],"normalization,":[57],"stop":[58],"word":[59],"removal,":[60],"lemmatization),":[62],"feature":[63],"extraction,":[64],"training,":[66],"evaluation":[68],"using":[69],"metrics":[71],"accuracy,":[74],"F1-score,":[75],"Matthews":[76],"Correlation":[77],"Coefficient":[78],"(MCC),":[79],"Cohen\u2019s":[81],"Kappa.":[82],"Experimental":[83],"results":[84],"demonstrate":[85],"that":[86,117],"the":[87,105,129],"+":[89],"SVM":[90],"outperforms":[92],"other":[93],"configurations,":[94],"achieving":[95],"90.2%":[96],"accuracy":[97],"F1-score":[100],"82.52%,":[102],"thus":[103],"highlighting":[104],"advantage":[106],"incorporating":[108],"context":[110],"into":[111],"vector":[112],"representation.":[113],"concludes":[116],"methods":[119],"TF-IDF":[121],"robust":[125],"improve":[127],"both":[128],"precision":[130],"generalizability":[132],"analysis":[135,166],"models.":[136],"Practical":[137],"implications":[138],"include":[139],"potential":[140],"applications":[141],"in":[142],"sentiment":[143],"analysis,":[144],"topic":[145],"modeling,":[146],"legal":[150],"healthcare":[152],"domains,":[153],"multilingual":[155],"contexts.":[156],"This":[157],"research":[158],"provides":[159],"a":[160],"foundation":[161],"developing":[163],"high-performance":[164],"systems":[167],"applicable":[168],"various":[170],"real-world":[171],"natural":[172],"language":[173],"processing":[174],"tasks.":[175]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2025-08-11T00:00:00"}