{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,10]],"date-time":"2026-01-10T03:40:29Z","timestamp":1768016429886,"version":"3.49.0"},"reference-count":109,"publisher":"Association for Computing Machinery (ACM)","issue":"2","license":[{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"ETH Zurich Research Grant","award":["ETH-10 22-1"],"award-info":[{"award-number":["ETH-10 22-1"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["Proc. ACM Interact. Mob. Wearable Ubiquitous Technol."],"published-print":{"date-parts":[[2024,5,13]]},"abstract":"<jats:p>Large language models such as GPT-3 and ChatGPT can mimic human-to-human conversation with unprecedented fidelity, which enables many applications such as conversational agents for education and non-player characters in video games. In this work, we investigate the underlying personality structure that a GPT-3-based chatbot expresses during conversations with a human. We conducted a user study to collect 147 chatbot personality descriptors from 86 participants while they interacted with the GPT-3-based chatbot for three weeks. Then, 425 new participants rated the 147 personality descriptors in an online survey. We conducted an exploratory factor analysis on the collected descriptors and show that, though overlapping, human personality models do not fully transfer to the chatbot's personality as perceived by humans. We also show that the perceived personality is significantly different from that of virtual personal assistants, where users focus rather on serviceability and functionality. We discuss the implications of ever-evolving large language models and the change they affect in users' perception of agent personalities.<\/jats:p>","DOI":"10.1145\/3659626","type":"journal-article","created":{"date-parts":[[2024,5,15]],"date-time":"2024-05-15T12:20:41Z","timestamp":1715775641000},"page":"1-36","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":10,"title":["The Personality Dimensions GPT-3 Expresses During Human-Chatbot Interactions"],"prefix":"10.1145","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1337-7670","authenticated-orcid":false,"given":"Nikola","family":"Kova\u010devi\u0107","sequence":"first","affiliation":[{"name":"ETH Zurich, Zurich, Switzerland"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9655-9519","authenticated-orcid":false,"given":"Christian","family":"Holz","sequence":"additional","affiliation":[{"name":"ETH Zurich, Zurich, Switzerland"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-9324-779X","authenticated-orcid":false,"given":"Markus","family":"Gross","sequence":"additional","affiliation":[{"name":"ETH Zurich, Zurich, Switzerland"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0158-1305","authenticated-orcid":false,"given":"Rafael","family":"Wampfler","sequence":"additional","affiliation":[{"name":"ETH Zurich, Zurich, Switzerland"}]}],"member":"320","published-online":{"date-parts":[[2024,5,15]]},"reference":[{"key":"e_1_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1007\/s40593-023-00340-7"},{"key":"e_1_2_1_2_1","unstructured":"Inworld AI. 2023. The Future of NPCs - What gamers demand from next-gen characters. techreport. https:\/\/inworld.ai\/whitepapers\/future-of-npcs"},{"key":"e_1_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1037\/h0073629"},{"key":"e_1_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/2702123.2702592"},{"key":"e_1_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3581441"},{"key":"e_1_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1177\/1088868306294907"},{"key":"e_1_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1751-9004.2008.00134.x"},{"key":"e_1_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/taffc.2017.2763134"},{"key":"e_1_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.2139\/ssrn.4337484"},{"key":"e_1_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/2697.003.0009"},{"key":"e_1_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1214\/aos\/1013699998"},{"key":"e_1_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.21437\/speechprosody.2018-45"},{"key":"e_1_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3290605.3300451"},{"key":"e_1_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2218523120"},{"key":"e_1_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-14343-9_39"},{"key":"e_1_2_1_16_1","doi-asserted-by":"publisher","unstructured":"Tom B. Brown Benjamin Mann Nick Ryder Melanie Subbiah Jared Kaplan Prafulla Dhariwal Arvind Neelakantan Pranav Shyam Girish Sastry Amanda Askell Sandhini Agarwal Ariel Herbert-Voss Gretchen Krueger Tom Henighan Rewon Child Aditya Ramesh Daniel M. Ziegler Jeffrey Wu Clemens Winter Christopher Hesse Mark Chen Eric Sigler Mateusz Litwin Scott Gray Benjamin Chess Jack Clark Christopher Berner Sam McCandlish Alec Radford Ilya Sutskever and Dario Amodei. 2020. Language Models are Few-Shot Learners. https:\/\/doi.org\/10.48550\/ARXIV.2005.14165","DOI":"10.48550\/ARXIV.2005.14165"},{"key":"e_1_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1007\/bf02289253"},{"key":"e_1_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1207\/s15327906mbr0102_10"},{"key":"e_1_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1080\/10447318.2020.1841438"},{"key":"e_1_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/thms.2013.2293535"},{"key":"e_1_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00779-011-0490-1"},{"key":"e_1_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1002\/pfi.21727"},{"key":"e_1_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3290605.3300705"},{"key":"e_1_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.5334\/jopd.57"},{"key":"e_1_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1016\/0191-8869(92)90236-i"},{"key":"e_1_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1017\/s1351324920000601"},{"key":"e_1_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3491102.3502014"},{"key":"e_1_2_1_28_1","doi-asserted-by":"publisher","unstructured":"Emily Dinan Stephen Roller Kurt Shuster Angela Fan Michael Auli and Jason Weston. 2018. Wizard of Wikipedia: Knowledge-Powered Conversational agents. arXiv. https:\/\/doi.org\/10.48550\/ARXIV.1811.01241","DOI":"10.48550\/ARXIV.1811.01241"},{"key":"e_1_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1037\/0033-295x.99.3.550"},{"key":"e_1_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1080\/02699939208411068"},{"key":"e_1_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1038\/1991031a0"},{"key":"e_1_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.sigdial-1.15"},{"key":"e_1_2_1_33_1","doi-asserted-by":"publisher","unstructured":"Marta Ferreira and Belem Barbosa. 2023. A Review on Chatbot Personality and Its Expected Effects on Users. In Trends Applications and Challenges of Chatbot Technology. IGI Global 222--243. https:\/\/doi.org\/10.4018\/978-1-6684-6234-8.ch010","DOI":"10.4018\/978-1-6684-6234-8.ch010"},{"key":"e_1_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3079628.3079693"},{"key":"e_1_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11023-020-09548-1"},{"key":"e_1_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-17705-8_13"},{"key":"e_1_2_1_37_1","volume-title":"Proceedings of the 1st Workshop on Personalization of Generative AI Systems (PERSONALIZE 2024","author":"Frisch Ivar","year":"2024","unstructured":"Ivar Frisch and Mario Giulianelli. 2024. LLM Agents in Interaction: Measuring Personality Consistency and Linguistic Alignment in Interacting Populations of Large Language Models. In Proceedings of the 1st Workshop on Personalization of Generative AI Systems (PERSONALIZE 2024). Association for Computational Linguistics, St. Julians, Malta, 102--111. https:\/\/aclanthology.org\/2024.personalize-1.9"},{"key":"e_1_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3534622"},{"key":"e_1_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/CoG51982.2022.9893689"},{"key":"e_1_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3381002"},{"key":"e_1_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.301"},{"key":"e_1_2_1_42_1","volume-title":"Language and individual differences: The search for universals in personality lexicons. Review of personality and social psychology 2, 1","author":"Goldberg Lewis R","year":"1981","unstructured":"Lewis R Goldberg. 1981. Language and individual differences: The search for universals in personality lexicons. Review of personality and social psychology 2, 1 (1981), 141--165."},{"key":"e_1_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1037\/0022-3514.59.6.1216"},{"key":"e_1_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1037\/1040-3590.4.1.26"},{"key":"e_1_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1037\/0003-066x.48.1.26"},{"key":"e_1_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1080\/19312450709336664"},{"key":"e_1_2_1_47_1","doi-asserted-by":"publisher","unstructured":"Javier Hernandez Jina Suh Judith Amores Kael Rowan Gonzalo Ramos and Mary Czerwinski. 2023. Affective Conversational Agents: Understanding Expectations and Personal Influences. https:\/\/doi.org\/10.48550\/ARXIV.2310.12459","DOI":"10.48550\/ARXIV.2310.12459"},{"key":"e_1_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.4135\/9780857028075"},{"key":"e_1_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1162\/pres.15.6.688"},{"key":"e_1_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11199-006-9158-0"},{"key":"e_1_2_1_51_1","doi-asserted-by":"publisher","unstructured":"Hang Jiang Xiajie Zhang Xubo Cao and Jad Kabbara. 2023. PersonaLLM: Investigating the Ability of GPT-3.5 to Express Personality Traits and Gender Differences. https:\/\/doi.org\/10.48550\/ARXIV.2305.02547","DOI":"10.48550\/ARXIV.2305.02547"},{"key":"e_1_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-04954-0_21"},{"key":"e_1_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1007\/bf02291817"},{"key":"e_1_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.nlp.2023.100048"},{"key":"e_1_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.lindif.2023.102274"},{"key":"e_1_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1145\/3214273"},{"key":"e_1_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-021-00464-x"},{"key":"e_1_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10639-022-11177-3"},{"key":"e_1_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.2307\/2529310"},{"key":"e_1_2_1_60_1","doi-asserted-by":"publisher","unstructured":"Xingxuan Li Yutong Li Shafiq Joty Linlin Liu Fei Huang Lin Qiu and Lidong Bing. 2022. Does GPT-3 Demonstrate Psychopathy? Evaluating Large Language Models from a Psychological Perspective. https:\/\/doi.org\/10.48550\/ARXIV.2212.10529","DOI":"10.48550\/ARXIV.2212.10529"},{"key":"e_1_2_1_61_1","volume-title":"Proceedings of The 8th International Joint Conference on Natural Language Processing (IJCNLP","author":"Li Yanran","year":"2017","unstructured":"Yanran Li, Hui Su, Xiaoyu Shen, Wenjie Li, Ziqiang Cao, and Shuzi Niu. 2017. DailyDialog: A Manually Labelled Multi-turn Dialogue Dataset. In Proceedings of The 8th International Joint Conference on Natural Language Processing (IJCNLP 2017)."},{"key":"e_1_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i09.7098"},{"key":"e_1_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1089\/cyber.2018.0110"},{"key":"e_1_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343413.3377993"},{"key":"e_1_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1145\/3406522.3446018"},{"key":"e_1_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.1145\/2858036.2858288"},{"key":"e_1_2_1_67_1","doi-asserted-by":"publisher","unstructured":"F. Mairesse M. A. Walker M. R. Mehl and R. K. Moore. 2007. Using Linguistic Cues for the Automatic Recognition of Personality in Conversation and Text. Journal of Artificial Intelligence Research 30 (nov 2007) 457--500. https:\/\/doi.org\/10.1613\/jair.2349","DOI":"10.1613\/jair.2349"},{"key":"e_1_2_1_68_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijhcs.2005.07.001"},{"key":"e_1_2_1_69_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-6494.1992.tb00970.x"},{"key":"e_1_2_1_70_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-04380-2_6"},{"key":"e_1_2_1_71_1","doi-asserted-by":"publisher","DOI":"10.1109\/taffc.2011.38"},{"key":"e_1_2_1_72_1","doi-asserted-by":"publisher","DOI":"10.1145\/3432193"},{"key":"e_1_2_1_73_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.nlpcss-1.24"},{"key":"e_1_2_1_74_1","doi-asserted-by":"publisher","DOI":"10.1109\/bigdata55660.2022.10020271"},{"key":"e_1_2_1_75_1","doi-asserted-by":"publisher","DOI":"10.1037\/h0040291"},{"key":"e_1_2_1_76_1","doi-asserted-by":"publisher","DOI":"10.1145\/2365952.2365957"},{"key":"e_1_2_1_77_1","doi-asserted-by":"publisher","DOI":"10.1037\/0022-3514.77.6.1296"},{"key":"e_1_2_1_78_1","doi-asserted-by":"publisher","DOI":"10.1145\/3469595.3469607"},{"key":"e_1_2_1_79_1","doi-asserted-by":"publisher","unstructured":"Angela Ramirez Mamon Alsalihy Kartik Aggarwal Cecilia Li Liren Wu and Marilyn Walker. 2023. Controlling Personality Style in Dialogue with Zero-Shot Prompt-Based Learning. https:\/\/doi.org\/10.48550\/ARXIV.2302.03848","DOI":"10.48550\/ARXIV.2302.03848"},{"key":"e_1_2_1_80_1","doi-asserted-by":"publisher","DOI":"10.1145\/1639714.1639779"},{"key":"e_1_2_1_81_1","doi-asserted-by":"publisher","DOI":"10.1177\/1470785320943049"},{"key":"e_1_2_1_82_1","doi-asserted-by":"publisher","DOI":"10.3390\/healthcare11060887"},{"key":"e_1_2_1_83_1","doi-asserted-by":"publisher","DOI":"10.1038\/d41586-023-00816-5"},{"key":"e_1_2_1_84_1","doi-asserted-by":"publisher","DOI":"10.1177\/2158244018769125"},{"key":"e_1_2_1_85_1","doi-asserted-by":"publisher","DOI":"10.1002\/9781118996874.ch8"},{"key":"e_1_2_1_86_1","doi-asserted-by":"publisher","DOI":"10.1145\/3462204.3481771"},{"key":"e_1_2_1_87_1","doi-asserted-by":"publisher","DOI":"10.12691\/ajams-9-1-2"},{"key":"e_1_2_1_88_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.chb.2020.106627"},{"key":"e_1_2_1_89_1","doi-asserted-by":"publisher","DOI":"10.1093\/ptj\/85.3.257"},{"key":"e_1_2_1_90_1","doi-asserted-by":"publisher","unstructured":"Marcin Skowron Marko Tkal\u010di\u010d Bruce Ferwerda and Markus Schedl. 2016. Fusing Social Media Cues: Personality Prediction from Twitter and Instagram. In Proceedings of the 25th International Conference Companion on World Wide Web (Montr\u00e9al Qu\u00e9bec Canada) (WWW '16 Companion). International World Wide Web Conferences Steering Committee Republic and Canton of Geneva CHE 107--108. https:\/\/doi.org\/10.1145\/2872518.2889368","DOI":"10.1145\/2872518.2889368"},{"key":"e_1_2_1_91_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-17705-8_15"},{"key":"e_1_2_1_92_1","doi-asserted-by":"publisher","DOI":"10.1037\/pspp0000096"},{"key":"e_1_2_1_93_1","doi-asserted-by":"publisher","DOI":"10.1186\/s40359-018-0257-9"},{"key":"e_1_2_1_94_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2016.2625250"},{"key":"e_1_2_1_95_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2902863"},{"key":"e_1_2_1_96_1","doi-asserted-by":"publisher","unstructured":"Teo Susnjak. 2022. ChatGPT: The End of Online Exam Integrity? https:\/\/doi.org\/10.48550\/ARXIV.2212.09292","DOI":"10.48550\/ARXIV.2212.09292"},{"key":"e_1_2_1_97_1","doi-asserted-by":"publisher","DOI":"10.1080\/13825585.2021.1872481"},{"key":"e_1_2_1_98_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397481.3450643"},{"key":"e_1_2_1_99_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2017.10.016"},{"key":"e_1_2_1_100_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0024-3795(97)10007-6"},{"key":"e_1_2_1_101_1","doi-asserted-by":"publisher","DOI":"10.2196\/16235"},{"key":"e_1_2_1_102_1","doi-asserted-by":"publisher","DOI":"10.1108\/josm-06-2019-0175"},{"key":"e_1_2_1_103_1","doi-asserted-by":"publisher","DOI":"10.1145\/3313831.3376210"},{"key":"e_1_2_1_104_1","doi-asserted-by":"publisher","DOI":"10.1145\/3491102.3502058"},{"key":"e_1_2_1_105_1","doi-asserted-by":"publisher","DOI":"10.1145\/3491102.3501835"},{"key":"e_1_2_1_106_1","doi-asserted-by":"publisher","DOI":"10.1386\/jgvw.9.1.39_1"},{"key":"e_1_2_1_107_1","doi-asserted-by":"publisher","unstructured":"Yixuan Weng Shizhu He Kang Liu Shengping Liu and Jun Zhao. 2024. ControlLM: Crafting Diverse Personalities for Language Models. https:\/\/doi.org\/10.48550\/ARXIV.2402.10151","DOI":"10.48550\/ARXIV.2402.10151"},{"key":"e_1_2_1_108_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20215"},{"key":"e_1_2_1_109_1","doi-asserted-by":"publisher","DOI":"10.1109\/smc.2019.8914583"}],"container-title":["Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3659626","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3659626","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T17:00:54Z","timestamp":1755882054000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3659626"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,13]]},"references-count":109,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2024,5,13]]}},"alternative-id":["10.1145\/3659626"],"URL":"https:\/\/doi.org\/10.1145\/3659626","relation":{},"ISSN":["2474-9567"],"issn-type":[{"value":"2474-9567","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,5,13]]},"assertion":[{"value":"2024-05-15","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}