{"id":"https://openalex.org/W4416035841","doi":"https://doi.org/10.18653/v1/2025.emnlp-main.1163","title":"Linguistic and Embedding-Based Profiling of Texts Generated by Humans and Large Language Models","display_name":"Linguistic and Embedding-Based Profiling of Texts Generated by Humans and Large Language Models","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416035841","doi":"https://doi.org/10.18653/v1/2025.emnlp-main.1163"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.emnlp-main.1163","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.1163","pdf_url":"https://aclanthology.org/2025.emnlp-main.1163.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 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.emnlp-main.1163.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5095765187","display_name":"Sergio E. Zanotto","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Sergio E. Zanotto","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5006658157","display_name":"Segun Aroyehun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Segun Aroyehun","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5095765187"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.52,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.95119142,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"22852","last_page":"22869"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12380","display_name":"Authorship Attribution and Profiling","score":0.5942000150680542,"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/T12380","display_name":"Authorship Attribution and Profiling","score":0.5942000150680542,"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":0.0658000037074089,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.059700001031160355,"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/profiling","display_name":"Profiling (computer programming)","score":0.5236999988555908},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.3131999969482422},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.2903999984264374},{"id":"https://openalex.org/keywords/computational-linguistics","display_name":"Computational linguistics","score":0.2628999948501587},{"id":"https://openalex.org/keywords/linguistic-analysis","display_name":"Linguistic analysis","score":0.241799995303154}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6013000011444092},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.5516999959945679},{"id":"https://openalex.org/C187191949","wikidata":"https://www.wikidata.org/wiki/Q1138496","display_name":"Profiling (computer programming)","level":2,"score":0.5236999988555908},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4894999861717224},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.428600013256073},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3131999969482422},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2903999984264374},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.2628999948501587},{"id":"https://openalex.org/C2987219923","wikidata":"https://www.wikidata.org/wiki/Q777864","display_name":"Linguistic analysis","level":2,"score":0.241799995303154},{"id":"https://openalex.org/C2777532361","wikidata":"https://www.wikidata.org/wiki/Q687185","display_name":"Lexicalization","level":2,"score":0.2345000058412552}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.emnlp-main.1163","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.1163","pdf_url":"https://aclanthology.org/2025.emnlp-main.1163.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 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.emnlp-main.1163","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.1163","pdf_url":"https://aclanthology.org/2025.emnlp-main.1163.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 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2367825995","display_name":null,"funder_award_id":"390681379","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"},{"id":"https://openalex.org/G3929093277","display_name":null,"funder_award_id":"EXC-2035/1","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"},{"id":"https://openalex.org/G5106512922","display_name":null,"funder_award_id":"Deutsche Forschungsgemeinschaft (DFG","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"}],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416035841.pdf","grobid_xml":"https://content.openalex.org/works/W4416035841.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0],"rapid":[1],"advancements":[2],"in":[3,159],"large":[4],"language":[5],"models":[6,142,176],"(LLMs)":[7],"have":[8],"significantly":[9],"improved":[10],"their":[11],"ability":[12],"to":[13,35,122,166,184],"generate":[14],"natural":[15],"language,":[16],"making":[17],"texts":[18,50,74,103,120,147,155],"generated":[19],"by":[20,80],"LLMs":[21,34],"increasingly":[22],"indistinguishable":[23],"from":[24],"human-written":[25,40,71,100,119,154,171],"texts.While":[26],"recent":[27],"research":[28],"has":[29],"primarily":[30],"focused":[31],"on":[32,47],"using":[33,51],"classify":[36],"text":[37,178],"as":[38,62,89],"either":[39],"or":[41],"machine-generated":[42,73,102,173,188],"texts,":[43],"our":[44,137,160],"study":[45],"focuses":[46],"characterizing":[48,99],"these":[49],"a":[52,68,185],"set":[53,138],"of":[54,70,136,139,187],"linguistic":[55,59,86],"features":[56,87,140],"across":[57,141,151],"different":[58,82,85,106],"levels":[60],"such":[61,88],"morphology,":[63],"syntax,":[64],"and":[65,72,78,92,94,101,111,127,143,172],"semantics.We":[66],"select":[67],"dataset":[69],"spanning":[75],"8":[76],"domains":[77],"produced":[79],"11":[81],"LLMs.We":[83],"calculate":[84,133],"dependency":[90],"length":[91],"emotionality,":[93],"we":[95,132,162],"use":[96],"them":[97],"for":[98],"along":[104],"with":[105,153],"sampling":[107],"strategies,":[108],"repetition":[109],"controls,":[110],"model":[112],"release":[113],"dates.Our":[114],"statistical":[115],"analysis":[116],"reveals":[117],"that":[118,179],"tend":[121],"exhibit":[123],"simpler":[124],"syntactic":[125],"structures":[126],"more":[128],"diverse":[129],"semantic":[130],"content.Furthermore,":[131],"the":[134],"variability":[135,169],"domains.Both":[144],"human-and":[145],"machinegenerated":[146],"show":[148],"stylistic":[149],"diversity":[150],"domains,":[152],"displaying":[156],"greater":[157],"variation":[158],"features.Finally,":[161],"apply":[163],"style":[164],"embeddings":[165],"further":[167],"test":[168],"among":[170],"texts.Notably,":[174],"newer":[175],"output":[177],"is":[180],"similarly":[181],"variable,":[182],"pointing":[183],"homogenization":[186],"texts.":[189]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-04-17T18:11:37.981687","created_date":"2025-11-08T00:00:00"}