{"id":"https://openalex.org/W4412747777","doi":"https://doi.org/10.1109/tcss.2025.3587039","title":"Feature Extraction and Compliance Classification of Text Files Using Large Language Models","display_name":"Feature Extraction and Compliance Classification of Text Files Using Large Language Models","publication_year":2025,"publication_date":"2025-07-30","ids":{"openalex":"https://openalex.org/W4412747777","doi":"https://doi.org/10.1109/tcss.2025.3587039"},"language":"en","primary_location":{"id":"doi:10.1109/tcss.2025.3587039","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcss.2025.3587039","pdf_url":null,"source":{"id":"https://openalex.org/S2490693980","display_name":"IEEE Transactions on Computational Social Systems","issn_l":"2329-924X","issn":["2329-924X","2373-7476"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Computational Social Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100668156","display_name":"Xiang Liu","orcid":"https://orcid.org/0000-0002-4874-4071"},"institutions":[{"id":"https://openalex.org/I2799850029","display_name":"Dongguan University of Technology","ror":"https://ror.org/01m8p7q42","country_code":"CN","type":"education","lineage":["https://openalex.org/I2799850029"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiang Liu","raw_affiliation_strings":["Institute of Science and Technology Innovation, Dongguan University of Technology, Dongguan, China"],"raw_orcid":"https://orcid.org/0000-0002-4874-4071","affiliations":[{"raw_affiliation_string":"Institute of Science and Technology Innovation, Dongguan University of Technology, Dongguan, China","institution_ids":["https://openalex.org/I2799850029"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yanghao Liao","orcid":"https://orcid.org/0009-0007-5088-2979"},"institutions":[{"id":"https://openalex.org/I101479585","display_name":"South China Agricultural University","ror":"https://ror.org/05v9jqt67","country_code":"CN","type":"education","lineage":["https://openalex.org/I101479585"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanghao Liao","raw_affiliation_strings":["College of Mathematics and Informatics, South China Agricultural University, Guangzhou, China"],"raw_orcid":"https://orcid.org/0009-0007-5088-2979","affiliations":[{"raw_affiliation_string":"College of Mathematics and Informatics, South China Agricultural University, Guangzhou, China","institution_ids":["https://openalex.org/I101479585"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004330040","display_name":"Zusheng Zhang","orcid":"https://orcid.org/0000-0002-4030-1663"},"institutions":[{"id":"https://openalex.org/I101479585","display_name":"South China Agricultural University","ror":"https://ror.org/05v9jqt67","country_code":"CN","type":"education","lineage":["https://openalex.org/I101479585"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zusheng Zhang","raw_affiliation_strings":["College of Mathematics and Informatics, South China Agricultural University, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-4030-1663","affiliations":[{"raw_affiliation_string":"College of Mathematics and Informatics, South China Agricultural University, Guangzhou, China","institution_ids":["https://openalex.org/I101479585"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jingcheng Hu","orcid":"https://orcid.org/0009-0006-1944-8202"},"institutions":[{"id":"https://openalex.org/I101479585","display_name":"South China Agricultural University","ror":"https://ror.org/05v9jqt67","country_code":"CN","type":"education","lineage":["https://openalex.org/I101479585"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingcheng Hu","raw_affiliation_strings":["College of Mathematics and Informatics, South China Agricultural University, Guangzhou, China"],"raw_orcid":"https://orcid.org/0009-0006-1944-8202","affiliations":[{"raw_affiliation_string":"College of Mathematics and Informatics, South China Agricultural University, Guangzhou, China","institution_ids":["https://openalex.org/I101479585"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029844813","display_name":"Lifeng Huang","orcid":"https://orcid.org/0000-0001-5162-9894"},"institutions":[{"id":"https://openalex.org/I101479585","display_name":"South China Agricultural University","ror":"https://ror.org/05v9jqt67","country_code":"CN","type":"education","lineage":["https://openalex.org/I101479585"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lifeng Huang","raw_affiliation_strings":["College of Mathematics and Informatics, South China Agricultural University, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-5162-9894","affiliations":[{"raw_affiliation_string":"College of Mathematics and Informatics, South China Agricultural University, Guangzhou, China","institution_ids":["https://openalex.org/I101479585"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":2645,"currency":"USD","value_usd":2645},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.24269238,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"12","issue":"6","first_page":"5106","last_page":"5117"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11644","display_name":"Spam and Phishing Detection","score":0.8040000200271606,"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"}},"topics":[{"id":"https://openalex.org/T11644","display_name":"Spam and Phishing Detection","score":0.8040000200271606,"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/T10400","display_name":"Network Security and Intrusion Detection","score":0.7386999726295471,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T11241","display_name":"Advanced Malware Detection Techniques","score":0.6912999749183655,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/computer-science","display_name":"Computer science","score":0.6349309086799622},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.6167404055595398},{"id":"https://openalex.org/keywords/compliance","display_name":"Compliance (psychology)","score":0.6008365154266357},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5833637714385986},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5080573558807373},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4842033386230469},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.38864701986312866},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3536337614059448},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.23513495922088623},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.11117199063301086}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6349309086799622},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.6167404055595398},{"id":"https://openalex.org/C2781460075","wikidata":"https://www.wikidata.org/wiki/Q1399332","display_name":"Compliance (psychology)","level":2,"score":0.6008365154266357},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5833637714385986},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5080573558807373},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4842033386230469},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.38864701986312866},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3536337614059448},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.23513495922088623},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.11117199063301086},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcss.2025.3587039","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcss.2025.3587039","pdf_url":null,"source":{"id":"https://openalex.org/S2490693980","display_name":"IEEE Transactions on Computational Social Systems","issn_l":"2329-924X","issn":["2329-924X","2373-7476"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Computational Social Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1911694105","display_name":null,"funder_award_id":"62172399","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4287865964","display_name":"\u5168\u5929\u5019\u884c\u4eba\u91cd\u8bc6\u522b\u6280\u672f\u7814\u7a76","funder_award_id":"62071122","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G850761804","display_name":null,"funder_award_id":"62472182","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W2266529343","https://openalex.org/W2781675902","https://openalex.org/W2888392466","https://openalex.org/W2936836598","https://openalex.org/W2995837271","https://openalex.org/W3197373672","https://openalex.org/W4283264034","https://openalex.org/W4285741594","https://openalex.org/W4313270711","https://openalex.org/W4313442940","https://openalex.org/W4381730576","https://openalex.org/W4389520455","https://openalex.org/W4392693783","https://openalex.org/W4393217356","https://openalex.org/W4400811147","https://openalex.org/W4402403052","https://openalex.org/W4403511074","https://openalex.org/W4404307311","https://openalex.org/W4405003679","https://openalex.org/W4406459892","https://openalex.org/W4410738232"],"related_works":["https://openalex.org/W2410395228","https://openalex.org/W3125941065","https://openalex.org/W2484615095","https://openalex.org/W4366449942","https://openalex.org/W4406616326","https://openalex.org/W4366371796","https://openalex.org/W4411216728","https://openalex.org/W4366371752","https://openalex.org/W4205440829","https://openalex.org/W1489027086"],"abstract_inverted_index":{"In":[0],"industries":[1],"such":[2,162],"as":[3,63,163],"finance,":[4],"healthcare,":[5],"and":[6,12,18,36,67,89,100,108,115,125,128,158,168],"new":[7],"energy":[8],"vehicles,":[9],"data":[10],"classification":[11,26,49,90,99,126,154],"grading":[13,88,129],"standards":[14,29],"ensure":[15],"regulatory":[16,64],"compliance":[17],"protect":[19],"sensitive":[20],"information.":[21],"However,":[22],"automating":[23],"text":[24,98,119],"file":[25],"under":[27],"these":[28,82],"presents":[30],"several":[31],"challenges.":[32],"Traditional":[33],"machine":[34],"learning":[35,38],"deep":[37],"approaches":[39,59],"require":[40],"large":[41],"labeled":[42],"datasets,":[43],"which":[44],"are":[45,51],"often":[46],"scarce.":[47],"Existing":[48],"methods":[50],"typically":[52],"domain-specific,":[53],"limiting":[54],"cross-domain":[55],"adaptability.":[56],"Moreover,":[57],"many":[58],"simply":[60],"categorize":[61],"documents":[62],"or":[65],"nonregulatory":[66],"assign":[68],"security":[69],"levels,":[70],"but":[71],"fail":[72],"to":[73,77,112,185],"map":[74],"them":[75],"accurately":[76],"specific":[78],"rules.":[79],"To":[80],"address":[81],"challenges,":[83],"this":[84],"article":[85],"proposes":[86],"prompt-driven":[87],"algorithm":[91],"(PGCA),":[92],"a":[93,104,135],"prompt":[94,110],"learning-based":[95],"method":[96],"for":[97],"grading.":[101],"PGCA":[102,152],"integrates":[103],"structured":[105],"feature":[106],"repository":[107],"SQL-inspired":[109],"templates":[111],"efficiently":[113],"extract":[114],"match":[116],"features":[117],"from":[118],"documents,":[120],"establishing":[121],"mappings":[122],"between":[123,156],"text,":[124],"rules":[127],"standards.":[130],"Furthermore,":[131],"the":[132,139,173],"integration":[133],"of":[134,141],"preclassification":[136,174],"strategy":[137],"enables":[138],"filtration":[140],"irrelevant":[142],"rules,":[143],"thereby":[144],"substantially":[145],"reducing":[146],"computational":[147,177],"overhead.":[148],"Experiments":[149],"show":[150],"that":[151],"achieves":[153],"accuracy":[155,183],"95.0%":[157],"99.0%,":[159],"outperforming":[160],"baselines":[161],"TsF-KNN,":[164],"Gen-DT,":[165],"bt-SVM,":[166],"AGCRCNN,":[167],"AC-BiLSTM":[169],"by":[170,179],"4%\u201325%.":[171],"Additionally,":[172],"stage":[175],"cuts":[176],"costs":[178],"63.7%":[180],"while":[181],"keeping":[182],"loss":[184],"within":[186],"1%.":[187]},"counts_by_year":[],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2025-10-10T00:00:00"}