{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T12:14:29Z","timestamp":1783944869412,"version":"3.55.0"},"reference-count":30,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T00:00:00Z","timestamp":1761350400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100004488","name":"Croatian Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004488","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Computers in Human Behavior: Artificial Humans"],"published-print":{"date-parts":[[2025,12]]},"DOI":"10.1016\/j.chbah.2025.100234","type":"journal-article","created":{"date-parts":[[2025,10,28]],"date-time":"2025-10-28T12:01:45Z","timestamp":1761652905000},"page":"100234","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":2,"special_numbering":"C","title":["Evaluating the agreement between human preferences, GPT-4V and Gemini Pro Vision assessments: Can AI recognize what people might like?"],"prefix":"10.1016","volume":"6","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4383-7807","authenticated-orcid":false,"given":"Dino","family":"Krupi\u0107","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3390-9467","authenticated-orcid":false,"given":"Domagoj","family":"Matijevi\u0107","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nenad","family":"\u0160uvak","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9078-6347","authenticated-orcid":false,"given":"Jurica","family":"Maltar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Domagoj","family":"\u0160everdija","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.chbah.2025.100234_bib1","series-title":"International conference on machine learning","first-page":"337","article-title":"Using large language models to simulate multiple humans and replicate human subject studies","author":"Aher","year":"2023"},{"key":"10.1016\/j.chbah.2025.100234_bib2","doi-asserted-by":"crossref","first-page":"875","DOI":"10.1038\/s41598-023-50229-7","article-title":"Humans create more novelty than ChatGPT when asked to retell a story","volume":"14","author":"Breithaupt","year":"2024","journal-title":"Scientific Reports"},{"key":"10.1016\/j.chbah.2025.100234_bib3","first-page":"1","article-title":"A simplified guide to determination of sample size requirements for estimating the value of intraclass correlation coefficient: A review","volume":"12","author":"Bujang","year":"2017","journal-title":"Archives of Orofacial Sciences"},{"key":"10.1016\/j.chbah.2025.100234_bib4","series-title":"2020 IEEE international conference on advances in electrical engineering and computer applications (AEECA), dalian, China","first-page":"113","article-title":"Restaurants' rating prediction using yelp dataset","author":"Chen","year":"2020"},{"key":"10.1016\/j.chbah.2025.100234_bib5","author":"Driessen"},{"key":"10.1016\/j.chbah.2025.100234_bib6","doi-asserted-by":"crossref","DOI":"10.3389\/fpsyg.2023.1199058","article-title":"ChatGPT outperforms humans in emotional awareness evaluations","volume":"14","author":"Elyoseph","year":"2023","journal-title":"Frontiers in Psychology"},{"issue":"1","key":"10.1016\/j.chbah.2025.100234_bib7","doi-asserted-by":"crossref","first-page":"201","DOI":"10.1002\/berj.4069","article-title":"Grading exams using large language models: A comparison between human and AI grading of exams in higher education using ChatGPT","volume":"51","author":"Flod\u00e9n","year":"2025","journal-title":"British Educational Research Journal"},{"key":"10.1016\/j.chbah.2025.100234_bib8","series-title":"Proceedings of the 48th international ACM SIGIR conference on research and development in information retrieval","first-page":"2858","article-title":"Large language model relevance assessors agree with one another more than with human assessors","author":"Fr\u00f6be","year":"2025"},{"key":"10.1016\/j.chbah.2025.100234_bib9","doi-asserted-by":"crossref","first-page":"833","DOI":"10.1038\/s43588-023-00527-x","article-title":"Human-like intuitive behavior and reasoning biases emerged in large language models but disappeared in ChatGPT","volume":"3","author":"Hagendorff","year":"2023","journal-title":"Nature Computational Science"},{"key":"10.1016\/j.chbah.2025.100234_bib10","doi-asserted-by":"crossref","first-page":"155","DOI":"10.1016\/j.jcm.2016.02.012","article-title":"A guideline of selecting and reporting intraclass correlation coefficients for reliability research","volume":"15","author":"Koo","year":"2016","journal-title":"Journal of chiropractic medicine"},{"key":"10.1016\/j.chbah.2025.100234_bib11","series-title":"Personality & intelligence: The psychology of individual differences","article-title":"Assessment: Methods, data, and interpretation","author":"Krupi\u0107","year":"2024"},{"key":"10.1016\/j.chbah.2025.100234_bib12","series-title":"International conference on internet (ICONI) 2023","article-title":"NLP models classifying helpful ratings in OpenTable dataset","author":"Lee","year":"2023"},{"key":"10.1016\/j.chbah.2025.100234_bib13","series-title":"2016 IEEE international conference on big data (IEEE BigData 2016)","first-page":"937","article-title":"Inferring restaurant styles by mining crowd-sourced photos from user-review websites","author":"Liao","year":"2016"},{"issue":"2","key":"10.1016\/j.chbah.2025.100234_bib14","doi-asserted-by":"crossref","DOI":"10.1016\/j.rmal.2025.100210","article-title":"Large language models fall short in classifying learners' open-ended responses","volume":"4","author":"Mizumoto","year":"2025","journal-title":"Research Methods in Applied Linguistics"},{"key":"10.1016\/j.chbah.2025.100234_bib15","doi-asserted-by":"crossref","DOI":"10.3389\/frai.2023.1199350","article-title":"Human-like problem-solving abilities in large language models using ChatGPT","volume":"6","author":"Orr\u00f9","year":"2023","journal-title":"Frontiers in artificial intelligence"},{"issue":"2","key":"10.1016\/j.chbah.2025.100234_bib16","doi-asserted-by":"crossref","first-page":"254","DOI":"10.1287\/mksc.2023.0454","article-title":"Frontiers: Determining the validity of large language models for automated perceptual analysis","volume":"43","author":"Peiyao Li","year":"2024","journal-title":"Marketing Science"},{"key":"10.1016\/j.chbah.2025.100234_bib17","series-title":"Personality & intelligence: The psychology of individual differences","article-title":"Motivation, emotions and personality","author":"Reisenzein","year":"2024"},{"key":"10.1016\/j.chbah.2025.100234_bib18","series-title":"Proceedings of the 8th international workshop on multimedia assisted dietary management (MADiMa '23)","first-page":"43","article-title":"Dining on details: LLM-guided expert networks for fine-grained food recognition","author":"Rodr\u00edguez-de-Vera","year":"2023"},{"key":"10.1016\/j.chbah.2025.100234_bib19","article-title":"Ranking-based scores for the assessment of aesthetic quality in photography","volume":"108","author":"Rubio","year":"2022","journal-title":"Signal Processing: Image Communication"},{"key":"10.1016\/j.chbah.2025.100234_bib20","doi-asserted-by":"crossref","first-page":"420","DOI":"10.1037\/0033-2909.86.2.420","article-title":"Intraclass correlations: Uses in assessing rater reliability","volume":"86","author":"Shrout","year":"1979","journal-title":"Psychological Bulletin"},{"key":"10.1016\/j.chbah.2025.100234_bib21","doi-asserted-by":"crossref","first-page":"1066","DOI":"10.1037\/xge0001547","article-title":"Do large language models show decision heuristics similar to humans? A case study using GPT-3.5","volume":"153","author":"Suri","year":"2024","journal-title":"Journal of Experimental Psychology: General"},{"key":"10.1016\/j.chbah.2025.100234_bib22","doi-asserted-by":"crossref","first-page":"175","DOI":"10.1016\/0022-2496(67)90049-1","article-title":"Additivity, utility, and subjective probability","volume":"4","author":"Tversky","year":"1967","journal-title":"Journal of Mathematical Psychology"},{"key":"10.1016\/j.chbah.2025.100234_bib23","doi-asserted-by":"crossref","first-page":"207","DOI":"10.1016\/0010-0285(73)90033-9","article-title":"Availability: A heuristic for judging frequency and probability","volume":"5","author":"Tversky","year":"1973","journal-title":"Cognitive Psychology"},{"issue":"8","key":"10.1016\/j.chbah.2025.100234_bib24","first-page":"178","article-title":"Biased by design? Evaluating bias and behavioral diversity in LLM annotation of real-world and synthetic hotel reviews","volume":"6","author":"Voutsa","year":"2025","journal-title":"AIAI"},{"key":"10.1016\/j.chbah.2025.100234_bib25","doi-asserted-by":"crossref","first-page":"1122","DOI":"10.1109\/JAS.2023.123618","article-title":"A brief overview of ChatGPT: The history, status quo and potential future development","volume":"10","author":"Wu","year":"2023","journal-title":"IEEE\/CAA Journal of Automatica Sinica"},{"key":"10.1016\/j.chbah.2025.100234_bib26","article-title":"DriveGPT4: Interpretable end-to-end autonomous driving via large language model","author":"Xu","year":"2024","journal-title":"arXiv preprint arXiv:2310.01412"},{"issue":"1","key":"10.1016\/j.chbah.2025.100234_bib27","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s12245-025-00895-3","article-title":"Evaluating large language models for renal colic imaging recommendations: A comparative analysis of gemini, copilot, and ChatGPT-4.0","volume":"18","author":"Yigit","year":"2025","journal-title":"International Journal of Emergency Medicine"},{"key":"10.1016\/j.chbah.2025.100234_bib28","article-title":"ArtGPT-4: Towards artistic-understanding large vision-language models with enhanced adapter","author":"Yuan","year":"2024","journal-title":"arXiv"},{"issue":"9","key":"10.1016\/j.chbah.2025.100234_bib29","doi-asserted-by":"crossref","first-page":"11602","DOI":"10.1109\/TITS.2024.3381175","article-title":"Vision-language models can identify distracted driver behavior from naturalistic videos","volume":"25","author":"Zahid Hasan","year":"2024","journal-title":"Trans. Intell. Transport. Sys."},{"key":"10.1016\/j.chbah.2025.100234_bib30","article-title":"GPT-4V as traffic assistant: An In-depth look at vision language model on complex traffic events","author":"Zhou","year":"2024","journal-title":"arXiv preprint arXiv:2402.02205"}],"updated-by":[{"DOI":"10.1016\/j.chbah.2026.100354","type":"erratum","label":"Erratum","source":"publisher","updated":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T00:00:00Z","timestamp":1783900800000}}],"container-title":["Computers in Human Behavior: Artificial Humans"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S2949882125001185?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S2949882125001185?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T01:20:04Z","timestamp":1783473604000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S2949882125001185"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12]]},"references-count":30,"alternative-id":["S2949882125001185"],"URL":"https:\/\/doi.org\/10.1016\/j.chbah.2025.100234","relation":{},"ISSN":["2949-8821"],"issn-type":[{"value":"2949-8821","type":"print"}],"subject":[],"published":{"date-parts":[[2025,12]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Evaluating the agreement between human preferences, GPT-4V and Gemini Pro Vision assessments: Can AI recognize what people might like?","name":"articletitle","label":"Article Title"},{"value":"Computers in Human Behavior: Artificial Humans","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.chbah.2025.100234","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2025 The Authors. Published by Elsevier Inc.","name":"copyright","label":"Copyright"}],"article-number":"100234"}}