{"id":"https://openalex.org/W4407781890","doi":"https://doi.org/10.1109/tai.2025.3544183","title":"AI-Generated Versus Human Text: Introducing a New Dataset for Benchmarking and Analysis","display_name":"AI-Generated Versus Human Text: Introducing a New Dataset for Benchmarking and Analysis","publication_year":2025,"publication_date":"2025-02-20","ids":{"openalex":"https://openalex.org/W4407781890","doi":"https://doi.org/10.1109/tai.2025.3544183"},"language":"en","primary_location":{"id":"doi:10.1109/tai.2025.3544183","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tai.2025.3544183","pdf_url":null,"source":{"id":"https://openalex.org/S4210169448","display_name":"IEEE Transactions on Artificial Intelligence","issn_l":"2691-4581","issn":["2691-4581"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1109/tai.2025.3544183","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103094335","display_name":"Ali Al Bataineh","orcid":"https://orcid.org/0000-0003-4576-2781"},"institutions":[{"id":"https://openalex.org/I169768744","display_name":"Norwich University","ror":"https://ror.org/04we7d902","country_code":"US","type":"education","lineage":["https://openalex.org/I169768744"]},{"id":"https://openalex.org/I4210151403","display_name":"Norwich University Applied Research Institute","ror":"https://ror.org/05bqezz06","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210151403"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ali Al Bataineh","raw_affiliation_strings":["Artificial Intelligence Center, Norwich University, Northfield, VT, USA","Artificial Intelligence Center, Norwich University, VT, USA"],"raw_orcid":"https://orcid.org/0000-0003-4576-2781","affiliations":[{"raw_affiliation_string":"Artificial Intelligence Center, Norwich University, Northfield, VT, USA","institution_ids":["https://openalex.org/I169768744","https://openalex.org/I4210151403"]},{"raw_affiliation_string":"Artificial Intelligence Center, Norwich University, VT, USA","institution_ids":["https://openalex.org/I169768744"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5116345913","display_name":"Rachel Sickler","orcid":null},"institutions":[{"id":"https://openalex.org/I4210151403","display_name":"Norwich University Applied Research Institute","ror":"https://ror.org/05bqezz06","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210151403"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rachel Sickler","raw_affiliation_strings":["Norwich University Applied Research Institutes, Northfield, VT, USA","Norwich University Applied Research Institutes, VT, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Norwich University Applied Research Institutes, Northfield, VT, USA","institution_ids":["https://openalex.org/I4210151403"]},{"raw_affiliation_string":"Norwich University Applied Research Institutes, VT, USA","institution_ids":["https://openalex.org/I4210151403"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5116345914","display_name":"Kerry Kurcz","orcid":null},"institutions":[{"id":"https://openalex.org/I4210151403","display_name":"Norwich University Applied Research Institute","ror":"https://ror.org/05bqezz06","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210151403"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kerry Kurcz","raw_affiliation_strings":["Norwich University Applied Research Institutes, Northfield, VT, USA","Norwich University Applied Research Institutes, VT, USA"],"raw_orcid":"https://orcid.org/0009-0002-9990-7886","affiliations":[{"raw_affiliation_string":"Norwich University Applied Research Institutes, Northfield, VT, USA","institution_ids":["https://openalex.org/I4210151403"]},{"raw_affiliation_string":"Norwich University Applied Research Institutes, VT, USA","institution_ids":["https://openalex.org/I4210151403"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038339592","display_name":"K Pedersen","orcid":null},"institutions":[{"id":"https://openalex.org/I4210151403","display_name":"Norwich University Applied Research Institute","ror":"https://ror.org/05bqezz06","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210151403"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kristen Pedersen","raw_affiliation_strings":["Norwich University Applied Research Institutes, Northfield, VT, USA"],"raw_orcid":"https://orcid.org/0009-0008-4655-9762","affiliations":[{"raw_affiliation_string":"Norwich University Applied Research Institutes, Northfield, VT, USA","institution_ids":["https://openalex.org/I4210151403"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":16.7519,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.98967693,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"6","issue":"8","first_page":"2241","last_page":"2252"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9921000003814697,"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":0.9921000003814697,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9883000254631042,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9855999946594238,"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/benchmarking","display_name":"Benchmarking","score":0.901038646697998},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5186538100242615},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4862314760684967},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40968939661979675},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3994942903518677},{"id":"https://openalex.org/keywords/business","display_name":"Business","score":0.12047994136810303}],"concepts":[{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.901038646697998},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5186538100242615},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4862314760684967},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40968939661979675},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3994942903518677},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.12047994136810303},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tai.2025.3544183","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tai.2025.3544183","pdf_url":null,"source":{"id":"https://openalex.org/S4210169448","display_name":"IEEE Transactions on Artificial Intelligence","issn_l":"2691-4581","issn":["2691-4581"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1109/tai.2025.3544183","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tai.2025.3544183","pdf_url":null,"source":{"id":"https://openalex.org/S4210169448","display_name":"IEEE Transactions on Artificial Intelligence","issn_l":"2691-4581","issn":["2691-4581"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1947481528","https://openalex.org/W2064675550","https://openalex.org/W2112796928","https://openalex.org/W2295598076","https://openalex.org/W2896457183","https://openalex.org/W2903950532","https://openalex.org/W2997591727","https://openalex.org/W3169509541","https://openalex.org/W4226186048","https://openalex.org/W4287833982","https://openalex.org/W4319991848","https://openalex.org/W4353007481","https://openalex.org/W4378765257","https://openalex.org/W4379538479","https://openalex.org/W4383751019","https://openalex.org/W4383815588","https://openalex.org/W4385156842","https://openalex.org/W4400762160"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W4238897586","https://openalex.org/W435179959","https://openalex.org/W2619091065","https://openalex.org/W2059640416","https://openalex.org/W1490753184","https://openalex.org/W2284465472","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Artificial":[0],"intelligence":[1],"(AI)":[2],"is":[3,45,60,67,128,147],"increasingly":[4],"embedded":[5],"in":[6,15,30],"our":[7,271],"everyday":[8],"lives.":[9],"With":[10],"the":[11,49,102,126,134,145,244,262,282,293],"introduction":[12],"of":[13,51,58,80,122,156],"ChatGPT":[14],"November":[16],"2022":[17],"by":[18,62],"OpenAI,":[19],"people":[20],"can":[21,260],"now":[22],"ask":[23],"a":[24,56,77,95,277],"bot":[25],"to":[26,47,53,93,98,111,254,264,276,290],"generate":[27,112],"comprehensive":[28],"writeups":[29],"seconds.":[31],"This":[32],"new":[33],"transformative":[34],"technology":[35],"also":[36,223],"introduces":[37],"ethical,":[38],"safety,":[39],"and":[40,75,87,90,131,138,167,186,204,210,219,235,257],"other":[41],"general":[42],"concerns.":[43],"It":[44],"important":[46],"harness":[48],"power":[50],"AI":[52,63],"understand":[54],"whether":[55,65],"body":[57],"text":[59,89,127,146],"generated":[61],"or":[64],"it":[66,92],"organically":[68],"human.":[69],"In":[70],"this":[71],"article,":[72],"we":[73,105,116,214,236,259,269],"create":[74],"curate":[76],"medium-sized":[78],"dataset":[79],"10":[81],"000":[82],"records":[83],"containing":[84],"both":[85],"human":[86],"machine-generated":[88],"utilize":[91],"train":[94],"reliable":[96],"model":[97,228,263,275],"accurately":[99],"distinguish":[100],"between":[101],"two.":[103],"First,":[104],"use":[106,243],"DistilGPT-2":[107],"with":[108,177,292],"various":[109],"inputs":[110],"machine":[113,211,251],"text.":[114,124],"Then,":[115],"acquire":[117],"an":[118,233],"equal":[119],"sample":[120],"size":[121],"human-generated":[123],"All":[125],"cleaned,":[129],"explored,":[130],"visualized":[132],"using":[133,151,281],"uniform":[135],"manifold":[136],"approximation":[137],"projection":[139],"(UMAP)":[140],"dimensionality":[141],"reduction":[142],"technique.":[143],"Finally,":[144],"transformed":[148],"into":[149],"vectors":[150],"several":[152],"techniques,":[153],"including":[154],"bag":[155],"words,":[157],"term":[158],"frequency-inverse":[159],"document":[160],"frequency,":[161],"bidirectional":[162],"encoder":[163],"representations":[164],"from":[165],"transformer,":[166],"neural":[168,201],"network-based":[169],"embeddings.":[170],"Machine":[171],"learning":[172,192,212,252],"experiments":[173],"are":[174],"then":[175,242],"performed":[176],"traditional":[178],"models":[179,193,253],"such":[180,194],"as":[181,188,190,195],"logistic":[182],"regression,":[183],"random":[184],"forest,":[185],"XGBoost,":[187],"well":[189],"deep":[191],"long":[196],"short-term":[197],"memory":[198],"(LSTM),":[199],"convolutional":[200],"network":[202],"(CNN),":[203],"CNN-LSTM.":[205],"Across":[206],"all":[207],"vectorization":[208],"strategies":[209],"algorithms,":[213],"measure":[215],"accuracy,":[216],"precision,":[217],"recall,":[218],"F1":[220],"scores.":[221],"We":[222,241],"time":[224],"each":[225],"exercise.":[226],"Each":[227],"completes":[229],"its":[230],"training":[231],"within":[232],"hour,":[234],"observe":[237],"scores":[238],"above":[239],"90%.":[240],"Shapley":[245],"additive":[246],"explanations":[247],"(SHAP)":[248],"package":[249],"on":[250],"explore":[255],"if":[256],"how":[258],"explain":[261],"further":[265],"validate":[266],"results.":[267],"Lastly,":[268],"deploy":[270],"TF-IDF":[272],"Random":[273],"Forest":[274],"user-friendly":[278],"web":[279],"application":[280],"Streamlit":[283],"framework,":[284],"allowing":[285],"users":[286],"without":[287],"coding":[288],"expertise":[289],"interact":[291],"model.":[294]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":6}],"updated_date":"2025-12-22T23:10:17.713674","created_date":"2025-02-21T00:00:00"}