{"id":"https://openalex.org/W7151615940","doi":"https://doi.org/10.1109/icmla66185.2025.00030","title":"A Feature-based Linguistic and Statistical Framework for AI-Generated Text Detection","display_name":"A Feature-based Linguistic and Statistical Framework for AI-Generated Text Detection","publication_year":2025,"publication_date":"2025-12-03","ids":{"openalex":"https://openalex.org/W7151615940","doi":"https://doi.org/10.1109/icmla66185.2025.00030"},"language":null,"primary_location":{"id":"doi:10.1109/icmla66185.2025.00030","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icmla66185.2025.00030","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Machine Learning and Applications (ICMLA)","raw_type":"proceedings-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/A5121387158","display_name":"Vaishnavi Sen","orcid":null},"institutions":[{"id":"https://openalex.org/I157638225","display_name":"California State University, Northridge","ror":"https://ror.org/005f5hv41","country_code":"US","type":"education","lineage":["https://openalex.org/I157638225"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Vaishnavi Sen","raw_affiliation_strings":["California State University, Northridge,Computer Science,Los Angeles,United States"],"affiliations":[{"raw_affiliation_string":"California State University, Northridge,Computer Science,Los Angeles,United States","institution_ids":["https://openalex.org/I157638225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091820414","display_name":"Rashida Hasan","orcid":"https://orcid.org/0000-0002-6231-8116"},"institutions":[{"id":"https://openalex.org/I157638225","display_name":"California State University, Northridge","ror":"https://ror.org/005f5hv41","country_code":"US","type":"education","lineage":["https://openalex.org/I157638225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rashida Hasan","raw_affiliation_strings":["California State University, Northridge,Computer Science,Los Angeles,United States"],"affiliations":[{"raw_affiliation_string":"California State University, Northridge,Computer Science,Los Angeles,United States","institution_ids":["https://openalex.org/I157638225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5121387158"],"corresponding_institution_ids":["https://openalex.org/I157638225"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.8729798,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"184","last_page":"191"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.24729999899864197,"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":0.24729999899864197,"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":0.22939999401569366,"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":0.09920000284910202,"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/natural-language","display_name":"Natural language","score":0.3230000138282776},{"id":"https://openalex.org/keywords/statistical-analysis","display_name":"Statistical analysis","score":0.31459999084472656},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.3057999908924103},{"id":"https://openalex.org/keywords/computational-linguistics","display_name":"Computational linguistics","score":0.27810001373291016},{"id":"https://openalex.org/keywords/statistical-model","display_name":"Statistical model","score":0.26019999384880066}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6459000110626221},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5623000264167786},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5593000054359436},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3944000005722046},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3230000138282776},{"id":"https://openalex.org/C2986587452","wikidata":"https://www.wikidata.org/wiki/Q938438","display_name":"Statistical analysis","level":2,"score":0.31459999084472656},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3057999908924103},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.27810001373291016},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.26019999384880066},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.25270000100135803}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icmla66185.2025.00030","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icmla66185.2025.00030","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Machine Learning and Applications (ICMLA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6163179278373718}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W2888482885","https://openalex.org/W2951080837","https://openalex.org/W3034287667","https://openalex.org/W4389518647","https://openalex.org/W4389519206","https://openalex.org/W4392669928","https://openalex.org/W4392745757","https://openalex.org/W4393262489"],"related_works":[],"abstract_inverted_index":{"The":[0],"growing":[1],"fluency,":[2],"coherence,":[3],"and":[4,42,62,72,85,108,125,146,161,176,188],"semantic":[5,104],"plausibility":[6],"of":[7,34,60,83],"text":[8,22,26],"generated":[9],"by":[10],"large":[11],"language":[12],"models":[13],"(LLMs)":[14],"pose":[15],"significant":[16],"challenges":[17,29],"for":[18,53],"reliably":[19],"distinguishing":[20],"AI-generated":[21],"(AGT)":[23],"from":[24,31],"human-written":[25],"(HWT).":[27],"These":[28,112],"stem":[30],"the":[32,58,131],"absence":[33],"identifiable":[35],"stylistic":[36],"artifacts,":[37],"limited":[38],"generalization":[39],"across":[40,163],"domains,":[41],"performance":[43,173],"degradation":[44],"under":[45],"class":[46,165],"imbalance.":[47],"Accurate":[48],"AGT":[49,152,182],"detection":[50,76,183],"is":[51],"essential":[52],"upholding":[54],"academic":[55],"integrity,":[56],"limiting":[57],"spread":[59],"misinformation,":[61],"ensuring":[63],"transparent":[64],"authorship":[65],"attribution.":[66],"This":[67],"work":[68],"introduces":[69],"LISA":[70,171],"(Linguistic":[71],"Statistical":[73],"Analysis),":[74],"a":[75,80],"framework":[77],"that":[78,121,170],"extracts":[79],"comprehensive":[81],"set":[82],"linguistically":[84],"statistically":[86],"grounded":[87],"features,":[88],"including":[89,140,185],"lexical":[90],"richness":[91],"metrics,":[92],"entropy":[93],"measures,":[94],"repetition":[95],"frequency,":[96],"part-of-speech":[97],"tag":[98],"distributions,":[99],"syntactic":[100],"parse":[101],"tree":[102],"depth,":[103],"topic":[105],"drift":[106],"indicators,":[107],"sentence-level":[109],"coherence":[110],"scores.":[111],"features":[113],"are":[114],"systematically":[115],"encoded":[116],"into":[117],"fixed-length":[118],"feature":[119,133],"vectors":[120,134],"capture":[122],"both":[123],"shallow":[124],"deep":[126],"textual":[127],"patterns.":[128],"We":[129],"use":[130],"resulting":[132],"to":[135,150],"train":[136],"four":[137],"classical":[138],"models,":[139],"Random":[141],"Forest,":[142],"XGBoost,":[143],"Multilayer":[144],"Perceptron,":[145],"Support":[147],"Vector":[148],"Machine":[149],"evaluate":[151],"vs.":[153],"HWT":[154],"classification":[155],"on":[156],"two":[157],"benchmark":[158],"datasets,":[159],"XSum":[160],"HC3,":[162],"different":[164],"distributions.":[166],"Experimental":[167],"results":[168],"demonstrate":[169],"achieves":[172],"comparable":[174],"to,":[175],"in":[177],"several":[178],"settings":[179],"surpassing,":[180],"state-of-the-art":[181],"methods,":[184],"DetectGPT,":[186],"GPTZero,":[187],"RoBERTa.":[189]},"counts_by_year":[],"updated_date":"2026-04-09T06:08:40.794217","created_date":"2026-04-08T00:00:00"}