{"id":"https://openalex.org/W7220675136","doi":"https://doi.org/10.52465/joscex.v7i3.225","title":"OCR-integrated retrieval-augmented generation for PDF-document question answering system in vocational higher education","display_name":"OCR-integrated retrieval-augmented generation for PDF-document question answering system in vocational higher education","publication_year":2026,"publication_date":"2026-09-21","ids":{"openalex":"https://openalex.org/W7220675136","doi":"https://doi.org/10.52465/joscex.v7i3.225"},"language":"en","primary_location":{"id":"doi:10.52465/joscex.v7i3.225","doi":"https://doi.org/10.52465/joscex.v7i3.225","is_oa":true,"landing_page_url":"https://doi.org/10.52465/joscex.v7i3.225","pdf_url":"https://joscex.shmpublisher.com/index.php/journal/article/download/225/70","source":{"id":"https://openalex.org/S4210238082","display_name":"Journal of Soft Computing Exploration","issn_l":"2746-0991","issn":["2746-0991","2746-7686"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Soft Computing Exploration","raw_type":"journal-article"},"volume":null,"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://joscex.shmpublisher.com/index.php/journal/article/download/225/70","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5064321957","display_name":"Mutiara Auliya Khadija","orcid":"https://orcid.org/0000-0001-7649-5423","observed_orcids":["https://orcid.org/0000-0001-7649-5423"]},"institutions":[{"id":"https://openalex.org/I119896790","display_name":"Sebelas Maret University","ror":"https://ror.org/021hq5q33","country_code":"ID","type":"education","lineage":["https://openalex.org/I119896790"]}],"countries":["ID"],"is_corresponding":false,"raw_author_name":"Mutiara Auliya Khadija","raw_affiliation_strings":["Vocational School, Universitas Sebelas Maret, Indonesia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Vocational School, Universitas Sebelas Maret, Indonesia","institution_ids":["https://openalex.org/I119896790"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5157685075","display_name":"Muhamad Prayoga Putra Setyawandana","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I119896790","display_name":"Sebelas Maret University","ror":"https://ror.org/021hq5q33","country_code":"ID","type":"education","lineage":["https://openalex.org/I119896790"]}],"countries":["ID"],"is_corresponding":false,"raw_author_name":"Muhamad Prayoga Putra Setyawandana","raw_affiliation_strings":["Vocational School, Universitas Sebelas Maret, Indonesia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Vocational School, Universitas Sebelas Maret, Indonesia","institution_ids":["https://openalex.org/I119896790"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5143477993","display_name":"Muhammad Raihan","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I119896790","display_name":"Sebelas Maret University","ror":"https://ror.org/021hq5q33","country_code":"ID","type":"education","lineage":["https://openalex.org/I119896790"]}],"countries":["ID"],"is_corresponding":false,"raw_author_name":"Muhammad Raihan","raw_affiliation_strings":["Vocational School, Universitas Sebelas Maret, Indonesia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Vocational School, Universitas Sebelas Maret, Indonesia","institution_ids":["https://openalex.org/I119896790"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048669442","display_name":"Wahyu Nurharjadmo","orcid":"https://orcid.org/0009-0002-8395-9112","observed_orcids":["https://orcid.org/0009-0002-8395-9112"]},"institutions":[{"id":"https://openalex.org/I119896790","display_name":"Sebelas Maret University","ror":"https://ror.org/021hq5q33","country_code":"ID","type":"education","lineage":["https://openalex.org/I119896790"]}],"countries":["ID"],"is_corresponding":false,"raw_author_name":"Wahyu Nurharjadmo","raw_affiliation_strings":["Faculty of Social and Political Sciences, Universitas Sebelas Maret, Indonesia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Social and Political Sciences, Universitas Sebelas Maret, Indonesia","institution_ids":["https://openalex.org/I119896790"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004167276","display_name":"Ina Primasari","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I119896790","display_name":"Sebelas Maret University","ror":"https://ror.org/021hq5q33","country_code":"ID","type":"education","lineage":["https://openalex.org/I119896790"]}],"countries":["ID"],"is_corresponding":false,"raw_author_name":"Ina Primasari Primasari","raw_affiliation_strings":["Vocational School, Universitas Sebelas Maret, Indonesia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Vocational School, Universitas Sebelas Maret, Indonesia","institution_ids":["https://openalex.org/I119896790"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5157783966","display_name":"Abdul Aziz Aziz","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I119896790","display_name":"Sebelas Maret University","ror":"https://ror.org/021hq5q33","country_code":"ID","type":"education","lineage":["https://openalex.org/I119896790"]}],"countries":["ID"],"is_corresponding":false,"raw_author_name":"Abdul Aziz Aziz","raw_affiliation_strings":["Vocational School, Universitas Sebelas Maret, Indonesia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Vocational School, Universitas Sebelas Maret, Indonesia","institution_ids":["https://openalex.org/I119896790"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I119896790"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.77949857,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"7","issue":"3","first_page":"731","last_page":"743"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9771000146865845,"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/T10028","display_name":"Topic Modeling","score":0.9771000146865845,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.010700000450015068,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.0038999998942017555,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/retrieval-augmented-generation","display_name":"retrieval-augmented generation","score":0.972000002861023},{"id":"https://openalex.org/keywords/optical-character-recognition","display_name":"optical character recognition","score":0.906000018119812},{"id":"https://openalex.org/keywords/higher-vocational-education","display_name":"higher vocational education","score":0.9139999747276306},{"id":"https://openalex.org/keywords/institutional-documents","display_name":"institutional documents","score":0.8840000033378601},{"id":"https://openalex.org/keywords/document-ingestion","display_name":"document ingestion","score":0.6039999723434448},{"id":"https://openalex.org/keywords/semantic-search","display_name":"semantic search","score":0.6679999828338623},{"id":"https://openalex.org/keywords/text-chunking","display_name":"text chunking","score":0.5569999814033508},{"id":"https://openalex.org/keywords/ragas-evaluation","display_name":"RAGAS evaluation","score":0.8299999833106995},{"id":"https://openalex.org/keywords/answer-faithfulness","display_name":"answer faithfulness","score":0.5600000023841858}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6549999713897705},{"id":"https://openalex.org/C668760","wikidata":"https://www.wikidata.org/wiki/Q6869278","display_name":"Vocational education","level":2,"score":0.6496000289916992},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.6172999739646912},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5863000154495239},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5769000053405762},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.54339998960495},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.4726000130176544},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45910000801086426},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.44839999079704285},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4472000002861023},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.43209999799728394},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.4104999899864197},{"id":"https://openalex.org/C120912362","wikidata":"https://www.wikidata.org/wiki/Q136822","display_name":"Higher education","level":2,"score":0.38909998536109924},{"id":"https://openalex.org/C161156560","wikidata":"https://www.wikidata.org/wiki/Q1638872","display_name":"Document retrieval","level":2,"score":0.3605000078678131},{"id":"https://openalex.org/C148524875","wikidata":"https://www.wikidata.org/wiki/Q6975395","display_name":"F1 score","level":2,"score":0.31839999556541443},{"id":"https://openalex.org/C114010052","wikidata":"https://www.wikidata.org/wiki/Q150352","display_name":"Foreign language","level":2,"score":0.2971999943256378},{"id":"https://openalex.org/C58642233","wikidata":"https://www.wikidata.org/wiki/Q8269924","display_name":"Taxonomy (biology)","level":2,"score":0.2712000012397766},{"id":"https://openalex.org/C2781121862","wikidata":"https://www.wikidata.org/wiki/Q256","display_name":"Turkish","level":2,"score":0.25529998540878296},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.25369998812675476}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.52465/joscex.v7i3.225","doi":"https://doi.org/10.52465/joscex.v7i3.225","is_oa":true,"landing_page_url":"https://doi.org/10.52465/joscex.v7i3.225","pdf_url":"https://joscex.shmpublisher.com/index.php/journal/article/download/225/70","source":{"id":"https://openalex.org/S4210238082","display_name":"Journal of Soft Computing Exploration","issn_l":"2746-0991","issn":["2746-0991","2746-7686"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Soft Computing Exploration","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.52465/joscex.v7i3.225","doi":"https://doi.org/10.52465/joscex.v7i3.225","is_oa":true,"landing_page_url":"https://doi.org/10.52465/joscex.v7i3.225","pdf_url":"https://joscex.shmpublisher.com/index.php/journal/article/download/225/70","source":{"id":"https://openalex.org/S4210238082","display_name":"Journal of Soft Computing Exploration","issn_l":"2746-0991","issn":["2746-0991","2746-7686"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Soft Computing Exploration","raw_type":"journal-article"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G735757385","display_name":null,"funder_award_id":"460/UN27.22/PT.01.03/2026","funder_id":"https://openalex.org/F4320324621","funder_display_name":"Universitas Sebelas Maret"}],"funders":[{"id":"https://openalex.org/F4320324621","display_name":"Universitas Sebelas Maret","ror":"https://ror.org/021hq5q33"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7220675136.pdf","grobid_xml":"https://content.openalex.org/works/W7220675136.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W6949698826","https://openalex.org/W7115937668","https://openalex.org/W4412405871","https://openalex.org/W7163706527","https://openalex.org/W7213999465","https://openalex.org/W7161693333","https://openalex.org/W4405057528","https://openalex.org/W4408058069","https://openalex.org/W7163563603","https://openalex.org/W7214741040"],"abstract_inverted_index":{"Institutional":[0],"documents":[1,139],"in":[2,9,187],"vocational":[3],"higher":[4],"education":[5],"are":[6],"generally":[7],"stored":[8],"PDF":[10],"format":[11],"with":[12,96,136,144,160],"heterogeneous":[13],"characteristics,":[14],"including":[15],"both":[16],"digital":[17],"and":[18,49,65,70,106,122,171,195],"scanned":[19],"documents,":[20,88],"making":[21],"the":[22,87,153,172,189],"manual":[23],"information":[24],"retrieval":[25,194],"process":[26],"less":[27],"efficient.":[28],"This":[29,128],"study":[30],"aims":[31],"to":[32,40,192],"develop":[33],"an":[34],"OCR-Integrated":[35],"Retrieval-Augmented":[36],"Generation":[37,116],"(RAG)":[38],"system":[39,73],"support":[41],"PDF-document":[42],"question":[43,68],"answering":[44],"that":[45,152,181],"can":[46],"provide":[47],"accurate":[48],"traceable":[50],"document-based":[51],"answers.":[52],"The":[53,72,149],"proposed":[54],"framework":[55],"consists":[56],"of":[57,133,164,169],"three":[58],"main":[59],"stages":[60],"such":[61],"as":[62,82],"document":[63],"ingestion":[64],"processing,":[66],"retrieval-augmented":[67],"answering,":[69],"evaluation.":[71],"integrates":[74],"text":[75,89],"extraction":[76],"using":[77,113,130],"PyMuPDF,":[78],"Google":[79],"Tesseract":[80],"(v5.3.3)":[81],"a":[83,161,166,184],"OCR":[84],"fallback":[85],"for":[86],"cleaning,":[90],"chunking,":[91],"embedding":[92,155],"formation,":[93],"vector":[94],"storage":[95],"Facebook":[97],"AI":[98],"Similarity":[99],"Search":[100],"(FAISS),":[101],"semantic":[102],"retrieval,":[103],"prompt":[104],"augmentation,":[105],"answer":[107],"generation.":[108],"Evaluation":[109,124],"is":[110],"carried":[111],"out":[112],"Retrieval":[114],"Augmented":[115],"Assessment":[117],"(RAGAS)":[118],"Evaluation,":[119],"BERTScore":[120,173],"F1":[121,174],"Bilingual":[123],"Understudy":[125],"(BLEU)":[126],"Score.":[127],"experiment":[129],"50":[131],"total":[132],"PDF-documents":[134],"related":[135],"various":[137],"institutional":[138],"from":[140],"Vocational":[141],"Higher":[142],"Education":[143],"150":[145],"test":[146],"question-answer":[147],"queries.":[148],"results":[150],"show":[151],"Multilingual-e5-base":[154],"model":[156],"has":[157],"best":[158],"performed":[159],"context":[162],"precision":[163],"0.8333,":[165],"faithfulness":[167],"score":[168,175],"1.0000":[170],"reached":[176],"0.6494.":[177],"These":[178],"research":[179],"indicate":[180],"OCR-Integration":[182],"plays":[183],"critical":[185],"role":[186],"enabling":[188],"RAG":[190],"pipeline":[191],"improves":[193],"answer-generation":[196],"performance.":[197]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-10-07T00:00:00"}
