{"id":"https://openalex.org/W4404509397","doi":"https://doi.org/10.3389/frai.2024.1469197","title":"Investigating generative AI models and detection techniques: impacts of tokenization and dataset size on identification of AI-generated text","display_name":"Investigating generative AI models and detection techniques: impacts of tokenization and dataset size on identification of AI-generated text","publication_year":2024,"publication_date":"2024-11-19","ids":{"openalex":"https://openalex.org/W4404509397","doi":"https://doi.org/10.3389/frai.2024.1469197","pmid":"https://pubmed.ncbi.nlm.nih.gov/39628838"},"language":"en","primary_location":{"id":"doi:10.3389/frai.2024.1469197","is_oa":true,"landing_page_url":"https://doi.org/10.3389/frai.2024.1469197","pdf_url":"https://www.frontiersin.org/journals/artificial-intelligence/articles/10.3389/frai.2024.1469197/pdf","source":{"id":"https://openalex.org/S4210197006","display_name":"Frontiers in Artificial Intelligence","issn_l":"2624-8212","issn":["2624-8212"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.frontiersin.org/journals/artificial-intelligence/articles/10.3389/frai.2024.1469197/pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5008673508","display_name":"Haowei Hua","orcid":"https://orcid.org/0009-0003-8536-7441"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Haowei Hua","raw_affiliation_strings":["The Culver Academies, Culver, IN, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Culver Academies, Culver, IN, United States","institution_ids":[]}]},{"author_position":"last","author":{"id":null,"display_name":"Co-Jiayu Yao","orcid":null},"institutions":[{"id":"https://openalex.org/I70908550","display_name":"Anhui Polytechnic University","ror":"https://ror.org/041sj0284","country_code":"CN","type":"education","lineage":["https://openalex.org/I70908550"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Co-Jiayu Yao","raw_affiliation_strings":["Anhui Polytechnic University, Wuhu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Anhui Polytechnic University, Wuhu, China","institution_ids":["https://openalex.org/I70908550"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5008673508"],"corresponding_institution_ids":[],"apc_list":{"value":1150,"currency":"USD","value_usd":1150},"apc_paid":{"value":1150,"currency":"USD","value_usd":1150},"fwci":4.4929,"has_fulltext":true,"cited_by_count":15,"citation_normalized_percentile":{"value":0.95302864,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"7","issue":null,"first_page":"1469197","last_page":"1469197"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9955999851226807,"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"}},{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9830999970436096,"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/lexical-analysis","display_name":"Lexical analysis","score":0.7137200832366943},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.6876406669616699},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.6201818585395813},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6178977489471436},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6007548570632935},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4377908706665039},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.36209845542907715}],"concepts":[{"id":"https://openalex.org/C176982825","wikidata":"https://www.wikidata.org/wiki/Q835922","display_name":"Lexical analysis","level":2,"score":0.7137200832366943},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.6876406669616699},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.6201818585395813},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6178977489471436},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6007548570632935},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4377908706665039},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36209845542907715},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.3389/frai.2024.1469197","is_oa":true,"landing_page_url":"https://doi.org/10.3389/frai.2024.1469197","pdf_url":"https://www.frontiersin.org/journals/artificial-intelligence/articles/10.3389/frai.2024.1469197/pdf","source":{"id":"https://openalex.org/S4210197006","display_name":"Frontiers in Artificial Intelligence","issn_l":"2624-8212","issn":["2624-8212"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence","raw_type":"journal-article"},{"id":"pmid:39628838","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/39628838","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in artificial intelligence","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:11611853","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/11611853","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC11611853/pdf/frai-07-1469197.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Front Artif Intell","raw_type":"Text"},{"id":"pmh:oai:doaj.org/article:6d81dd9cc5f44836900bcc26ecc5861f","is_oa":true,"landing_page_url":"https://doaj.org/article/6d81dd9cc5f44836900bcc26ecc5861f","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Frontiers in Artificial Intelligence, Vol 7 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3389/frai.2024.1469197","is_oa":true,"landing_page_url":"https://doi.org/10.3389/frai.2024.1469197","pdf_url":"https://www.frontiersin.org/journals/artificial-intelligence/articles/10.3389/frai.2024.1469197/pdf","source":{"id":"https://openalex.org/S4210197006","display_name":"Frontiers in Artificial Intelligence","issn_l":"2624-8212","issn":["2624-8212"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.8799999952316284,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4404509397.pdf"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W2075424814","https://openalex.org/W2295598076","https://openalex.org/W2768149277","https://openalex.org/W2896457183","https://openalex.org/W2965373594","https://openalex.org/W3015657179","https://openalex.org/W4256049924","https://openalex.org/W4287824654","https://openalex.org/W4353007481","https://openalex.org/W4360891421","https://openalex.org/W4364387756","https://openalex.org/W4367172365","https://openalex.org/W4381515751","https://openalex.org/W4385156842","https://openalex.org/W4385488586","https://openalex.org/W4388034851","https://openalex.org/W4388108480","https://openalex.org/W4390175962","https://openalex.org/W4391169883","https://openalex.org/W4391603678","https://openalex.org/W4392405137","https://openalex.org/W4393146362","https://openalex.org/W4394707607","https://openalex.org/W4396912870","https://openalex.org/W4401184393","https://openalex.org/W6848670183","https://openalex.org/W6850824531","https://openalex.org/W6853668220","https://openalex.org/W6855235709"],"related_works":["https://openalex.org/W4405003489","https://openalex.org/W4386014872","https://openalex.org/W1847536016","https://openalex.org/W4361193986","https://openalex.org/W4300598845","https://openalex.org/W2601638452","https://openalex.org/W2285263069","https://openalex.org/W4376107815","https://openalex.org/W4319309671","https://openalex.org/W4319309603"],"abstract_inverted_index":{"Generative":[0],"AI":[1,54,95,160,200],"models,":[2,103,161],"including":[3,104,125],"ChatGPT,":[4,164],"Gemini,":[5],"and":[6,31,73,108,118,128,132,158,166,172,186,188,208],"Claude,":[7,165],"are":[8,112,130],"increasingly":[9],"significant":[10],"in":[11,96,168,217],"enhancing":[12],"K-12":[13],"education,":[14],"offering":[15],"support":[16,109],"across":[17],"various":[18,155],"disciplines.":[19],"These":[20],"models":[21,124],"provide":[22],"sample":[23],"answers":[24,51],"for":[25,77],"humanities":[26],"prompts,":[27],"solve":[28],"mathematical":[29],"equations,":[30],"brainstorm":[32],"novel":[33],"ideas.":[34],"Despite":[35],"their":[36,44,169],"educational":[37],"value,":[38],"ethical":[39],"concerns":[40],"have":[41],"emerged":[42],"regarding":[43],"potential":[45],"to":[46,68,114,134,197,213],"mislead":[47],"students":[48],"into":[49],"copying":[50],"directly":[52],"from":[53,145],"when":[55],"completing":[56],"assignments,":[57],"assessments,":[58],"or":[59],"research":[60],"papers.":[61],"Current":[62],"detectors,":[63],"such":[64,183],"as":[65,79,184],"GPT-Zero,":[66],"struggle":[67],"identify":[69],"modified":[70],"AI-generated":[71,117],"texts":[72],"show":[74],"reduced":[75],"reliability":[76],"English":[78],"a":[80,190],"Second":[81],"Language":[82],"learners.":[83],"This":[84],"study":[85],"investigates":[86],"detection":[87,156],"of":[88,93,154,180,193],"academic":[89],"cheating":[90],"by":[91],"use":[92],"generative":[94,159],"high-stakes":[97],"writing":[98],"assessments.":[99],"Classical":[100],"machine":[101,136],"learning":[102,137],"logistic":[105],"regression,":[106],"XGBoost,":[107],"vector":[110],"machine,":[111],"used":[113],"distinguish":[115],"between":[116,205],"student-written":[119],"essays.":[120],"Additionally,":[121,202],"large":[122],"language":[123],"BERT,":[126],"RoBERTa,":[127],"Electra":[129],"examined":[131],"compared":[133],"traditional":[135],"models.":[138],"The":[139],"analysis":[140],"focuses":[141],"on":[142],"prompt":[143],"1":[144],"the":[146,152,178,203],"ASAP":[147],"Kaggle":[148],"competition.":[149],"To":[150],"evaluate":[151],"effectiveness":[153],"methods":[157],"we":[162,176],"include":[163],"Gemini":[167],"base,":[170],"pro,":[171],"latest":[173],"versions.":[174],"Furthermore,":[175],"examine":[177],"impact":[179],"paraphrasing":[181],"tools":[182],"GPT-Humanizer":[185],"QuillBot":[187],"introduce":[189],"new":[191],"method":[192],"using":[194],"synonym":[195],"information":[196],"detect":[198],"humanized":[199],"texts.":[201],"relationship":[204],"dataset":[206],"size":[207],"model":[209],"performance":[210],"is":[211],"explored":[212],"inform":[214],"data":[215],"collection":[216],"future":[218],"research.":[219]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":9}],"updated_date":"2026-06-24T13:16:06.693445","created_date":"2025-10-10T00:00:00"}