{"id":"https://openalex.org/W4412889229","doi":"https://doi.org/10.18653/v1/2025.bea-1.71","title":"Can GPTZero\u2019s AI Vocabulary Distinguish Between LLM-Generated and Student-Written Essays?","display_name":"Can GPTZero\u2019s AI Vocabulary Distinguish Between LLM-Generated and Student-Written Essays?","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412889229","doi":"https://doi.org/10.18653/v1/2025.bea-1.71"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.bea-1.71","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.bea-1.71","pdf_url":"https://aclanthology.org/2025.bea-1.71.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 20th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2025)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.bea-1.71.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5082093975","display_name":"Veronica Juliana Schmalz","orcid":"https://orcid.org/0000-0002-1636-6133"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Veronica Schmalz","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5044580735","display_name":"Ana\u00efs Tack","orcid":"https://orcid.org/0000-0003-3086-8188"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ana\u00efs Tack","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.14578439,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"937","last_page":"952"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9850000143051147,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9850000143051147,"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/T13629","display_name":"Text Readability and Simplification","score":0.9643999934196472,"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":0.9197999835014343,"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/computer-science","display_name":"Computer science","score":0.692351758480072},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.643413782119751},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5626757144927979},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4905780851840973},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.32289159297943115},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.06519672274589539}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.692351758480072},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.643413782119751},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5626757144927979},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4905780851840973},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.32289159297943115},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.06519672274589539}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.18653/v1/2025.bea-1.71","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.bea-1.71","pdf_url":"https://aclanthology.org/2025.bea-1.71.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 20th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2025)","raw_type":"proceedings-article"},{"id":"pmh:oai:lirias2repo.kuleuven.be:20.500.12942/769441","is_oa":false,"landing_page_url":"https://lirias.kuleuven.be/handle/20.500.12942/769441","pdf_url":null,"source":{"id":"https://openalex.org/S7407055369","display_name":"Lirias","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":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"The 63rd Annual Meeting of the Association for Computational Linguistics, Vienna, Austria, 27 July - 1 August 2025","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.bea-1.71","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.bea-1.71","pdf_url":"https://aclanthology.org/2025.bea-1.71.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 20th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2025)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6800000071525574,"display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321730","display_name":"Fonds Wetenschappelijk Onderzoek","ror":"https://ror.org/03qtxy027"},{"id":"https://openalex.org/F4320327336","display_name":"Vlaamse regering","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412889229.pdf","grobid_xml":"https://content.openalex.org/works/W4412889229.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Despite":[0],"recent":[1],"advances":[2],"in":[3,11],"AI":[4,20,29,33,73,85,117,142,164,183],"detection":[5],"methods,":[6],"their":[7,124,209],"practical":[8],"application,":[9],"especially":[10],"education,":[12],"remains":[13],"limited.Educators":[14],"need":[15],"functional":[16],"tools":[17],"pointing":[18],"to":[19,43,92,127,154,158,170,188],"indicators":[21],"within":[22],"texts,":[23,54],"rather":[24],"than":[25,176],"merely":[26],"estimating":[27],"whether":[28,71],"was":[30],"used.GPTZero's":[31],"new":[32],"Vocabulary":[34,74,86,118,165,184],"feature,":[35],"which":[36,105],"highlights":[37],"parts":[38],"of":[39,101,140],"a":[40,56,99],"text":[41],"likely":[42],"be":[44],"AI-generated":[45],"based":[46,180,203],"on":[47,98,181,193,205],"frequent":[48],"words":[49],"and":[50,80,95,108,122,217],"phrases":[51],"from":[52,89],"LLM-generated":[53,79],"offers":[55],"potential":[57],"solution.However,":[58],"its":[59],"effectiveness":[60,213],"has":[61],"not":[62,137,167],"yet":[63],"been":[64],"empirically":[65],"validated.In":[66],"this":[67],"study,":[68],"we":[69],"examine":[70,123],"GPTZero's":[72,116,163,182],"can":[75],"effectively":[76],"distinguish":[77],"between":[78],"student-written":[81],"essays.We":[82,110],"analyze":[83],"the":[84,102,135,138,145,194],"lists":[87],"published":[88],"October":[90],"2024":[91],"March":[93],"2025":[94],"evaluate":[96],"them":[97],"subset":[100],"Ghostbuster":[103],"dataset,":[104],"includes":[106],"student":[107],"LLM":[109],"train":[111],"multiple":[112],"Bag-of-Words":[113,189],"classifiers":[114,179,190],"using":[115],"terms":[119,143],"as":[120],"features":[121],"individual":[125],"contributions":[126],"classification.Our":[128],"findings":[129,198],"show":[130],"that":[131,162,200],"simply":[132],"checking":[133],"for":[134],"presence,":[136],"frequency,":[139],"specific":[141],"yields":[144],"best":[146],"results,":[147],"particularly":[148],"with":[149],"ChatGPT-generated":[150],"essays.However,":[151],"performance":[152],"drops":[153],"near-random":[155],"when":[156],"applied":[157],"Claude-generated":[159],"essays,":[160],"indicating":[161],"may":[166],"generalize":[168],"well":[169],"texts":[171],"generated":[172],"by":[173],"LLMs":[174,216],"other":[175],"ChatGPT.Additionally,":[177],"all":[178],"significantly":[185],"underperform":[186],"compared":[187],"trained":[191],"directly":[192],"full":[195],"dataset":[196],"vocabulary.These":[197],"suggest":[199],"fixed":[201],"vocabularies":[202],"solely":[204],"lexical":[206],"features,":[207],"despite":[208],"interpretability,":[210],"have":[211],"limited":[212],"across":[214],"different":[215],"educational":[218],"writing":[219],"contexts.":[220]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}