{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,3]],"date-time":"2026-11-03T22:20:06Z","timestamp":1793744406743,"version":"4.6.1"},"reference-count":48,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2024,9,16]],"date-time":"2024-09-16T00:00:00Z","timestamp":1726444800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Artif. Intell."],"abstract":"<jats:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>Recent advances in generative Artificial Intelligence (AI) and Natural Language Processing (NLP) have led to the development of Large Language Models (LLMs) and AI-powered chatbots like ChatGPT, which have numerous practical applications. Notably, these models assist programmers with coding queries, debugging, solution suggestions, and providing guidance on software development tasks. Despite known issues with the accuracy of ChatGPT\u2019s responses, its comprehensive and articulate language continues to attract frequent use. This indicates potential for ChatGPT to support educators and serve as a virtual tutor for students.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>To explore this potential, we conducted a comprehensive analysis comparing the emotional content in responses from ChatGPT and human answers to 2000 questions sourced from Stack Overflow (SO). The emotional aspects of the answers were examined to understand how the emotional tone of AI responses compares to that of human responses.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Our analysis revealed that ChatGPT\u2019s answers are generally more positive compared to human responses. In contrast, human answers often exhibit emotions such as anger and disgust. Significant differences were observed in emotional expressions between ChatGPT and human responses, particularly in the emotions of anger, disgust, and joy. Human responses displayed a broader emotional spectrum compared to ChatGPT, suggesting greater emotional variability among humans.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Discussion<\/jats:title>\n                    <jats:p>The findings highlight a distinct emotional divergence between ChatGPT and human responses, with ChatGPT exhibiting a more uniformly positive tone and humans displaying a wider range of emotions. This variance underscores the need for further research into the role of emotional content in AI and human interactions, particularly in educational contexts where emotional nuances can impact learning and communication.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/frai.2024.1393903","type":"journal-article","created":{"date-parts":[[2024,9,16]],"date-time":"2024-09-16T01:10:41Z","timestamp":1726449041000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":13,"title":["Comparing emotions in ChatGPT answers and human answers to the coding questions on Stack Overflow"],"prefix":"10.3389","volume":"7","author":[{"given":"Somayeh","family":"Fatahi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Julita","family":"Vassileva","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chanchal K.","family":"Roy","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2024,9,16]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"427","DOI":"10.1007\/s12525-020-00414-7","article-title":"AI-based chatbots in customer service and their effects on user compliance","volume":"31","author":"Adam","year":"2021","journal-title":"Electron. Mark."},{"key":"ref2","author":"Adamopoulou","year":"2020"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.14569\/IJACSA.2015.060121","article-title":"A survey of topic modeling in text mining","volume":"6","author":"Alghamdi","year":"2015","journal-title":"Int. J. Adv. Comput. Sci. Appl.(IJACSA)"},{"key":"ref4","doi-asserted-by":"publisher","first-page":"2029","DOI":"10.5267\/j.ijdns.2023.6.010","article-title":"The impact of ChatGPT on blended learning: current trends and future research directions","volume":"7","author":"Alshahrani","year":"2023","journal-title":"Int J Data and Network Sci"},{"key":"ref5","first-page":"993","article-title":"Latent dirichlet allocation","volume":"3","author":"Blei","year":"2003","journal-title":"J. Mach. Learn. Res."},{"key":"ref6","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1080\/0163853X.2021.1899369","article-title":"Introduction to the special issue on emotions in reading, learning, and communication","volume":"59","author":"Bohn-Gettler","year":"2022","journal-title":"Discourse Process."},{"key":"ref7","volume-title":"Unraveling the impact: An empirical investigation of ChatGPT\u2019s exclusion from stack overflow","author":"Borwankar","year":"2023"},{"key":"ref8","first-page":"387","article-title":"ChatGPT goes to law school","volume":"71","author":"Choi","year":"2021","journal-title":"J. Leg. Educ."},{"key":"ref9","author":"Delile","year":"2023"},{"key":"ref10","first-page":"04805","article-title":"Bert: pre-training of deep bidirectional transformers for language understanding","volume":"1810","author":"Devlin","year":"2018","journal-title":"arXiv preprint arXiv"},{"key":"ref11","volume-title":"Schools ban ChatGPT amid fears of artificial intelligence-assisted cheating","author":"Dibble","year":"2023"},{"key":"ref12","doi-asserted-by":"crossref","first-page":"169","DOI":"10.1080\/02699939208411068","article-title":"An argument for basic emotions","volume":"6","author":"Ekman","year":"1992","journal-title":"Cognit. Emot."},{"key":"ref13","doi-asserted-by":"crossref","first-page":"1199058","DOI":"10.3389\/fpsyg.2023.1199058","article-title":"ChatGPT outperforms humans in emotional awareness evaluations","volume":"14","author":"Elyoseph","year":"2023","journal-title":"Front. Psychol."},{"key":"ref14","doi-asserted-by":"crossref","DOI":"10.4324\/9781315086071","volume-title":"The laws of emotion","author":"Frijda","year":"2017"},{"key":"ref15","author":"Grudin","year":"2019"},{"key":"ref16","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s12186-019-09226-z","article-title":"Emotions in learning at work: a literature review","volume":"13","author":"H\u00f6kk\u00e4","year":"2020","journal-title":"Vocat. Learn."},{"key":"ref17","author":"Jalil","year":"2023"},{"key":"ref18","first-page":"02312","article-title":"Who answers it better? An in-depth analysis of chatgpt and stack overflow answers to software engineering questions","volume":"2308","author":"Kabir","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref19","article-title":"Study and analysis of chat GPT and its impact on different fields of study","volume":"8","author":"Kalla","year":"2023","journal-title":"Int J Innovative Sci Res Technol"},{"key":"ref20","doi-asserted-by":"crossref","first-page":"102274","DOI":"10.1016\/j.lindif.2023.102274","article-title":"ChatGPT for good? On opportunities and challenges of large language models for education","volume":"103","author":"Kasneci","year":"2023","journal-title":"Learn. Individ. Differ."},{"key":"ref21","author":"Khoury","year":"2023"},{"key":"ref22","doi-asserted-by":"publisher","first-page":"e0000198","DOI":"10.1371\/journal.pdig.0000198","article-title":"Performance of ChatGPT on USMLE: potential for AI-assisted medical education using large language models","volume":"2","author":"Kung","year":"2023","journal-title":"PLoS Digital Health"},{"key":"ref23","author":"Li","year":"2023"},{"key":"ref24","first-page":"13851","article-title":"Which is a better programming assistant? A comparative study between chatgpt and stack overflow","volume":"2308","author":"Liu","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref25","doi-asserted-by":"crossref","first-page":"387","DOI":"10.1007\/978-3-031-37776-1_17","article-title":"Open AI in education, the responsible and ethical use of ChatGPT towards lifelong learning","volume-title":"FinTech and artificial intelligence for sustainable development: The role of smart technologies in achieving development goals","author":"Mhlanga","year":"2023"},{"key":"ref26","author":"Mohammad","year":"2018"},{"key":"ref27","doi-asserted-by":"publisher","first-page":"20","DOI":"10.55529\/ijitc.35.20.25","article-title":"Adopting ChatGPT to enhance educational experiences","volume":"3","author":"Murad","year":"2023","journal-title":"Int J Info Technol Comp Eng"},{"key":"ref28","doi-asserted-by":"publisher","first-page":"1072","DOI":"10.1080\/00207594.2012.753149","article-title":"Level of emotional awareness in the general French population: effects of gender, age, and education level","volume":"48","author":"Nandrino","year":"2013","journal-title":"Int. J. Psychol."},{"key":"ref29","first-page":"11837","article-title":"Comparing software developers with chatgpt: an empirical investigation","volume":"2305","author":"Nascimento","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref30","doi-asserted-by":"publisher","first-page":"103476","DOI":"10.1016\/j.cose.2023.103476","article-title":"Investigating ChatGPT and cybersecurity: a perspective on topic modeling and sentiment analysis","volume":"135","author":"Okey","year":"2023","journal-title":"Comput. Secur."},{"key":"ref31","unstructured":"2023"},{"key":"ref32","first-page":"27730","article-title":"Training language models to follow instructions with human feedback","volume":"35","author":"Ouyang","year":"2022","journal-title":"Adv. Neural Inf. Proces. Syst."},{"key":"ref33","first-page":"09774","article-title":"Emotionally-aware chatbots: a survey","volume":"1906","author":"Pamungkas","year":"2019","journal-title":"arXiv preprint arXiv"},{"key":"ref34","doi-asserted-by":"publisher","first-page":"721","DOI":"10.3928\/01484834-20231006-02","article-title":"ChatGPT for automated writing evaluation in scholarly writing instruction","volume":"62","author":"Parker","year":"2023","journal-title":"J. Nurs. Educ."},{"key":"ref35","volume-title":"Emotions in social psychology: Essential readings","author":"Parrott","year":"2001"},{"key":"ref36","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1016\/B978-0-12-558701-3.50007-7","article-title":"A general psychoevolutionary theory of emotion","volume-title":"Theories of emotion","author":"Plutchik","year":"1980"},{"key":"ref37","unstructured":"Poremba\n              S.\n            \n          \n          \n          2023"},{"key":"ref38","doi-asserted-by":"publisher","first-page":"102630","DOI":"10.1016\/j.ijhcs.2021.102630","article-title":"The human side of human-chatbot interaction: a systematic literature review of ten years of research on text-based chatbots","volume":"151","author":"Rapp","year":"2021","journal-title":"Int J Human-Computer Stud"},{"key":"ref39","doi-asserted-by":"publisher","first-page":"1161","DOI":"10.1037\/h0077714","article-title":"A circumplex model of affect","volume":"39","author":"Russell","year":"1980","journal-title":"J. Pers. Soc. Psychol."},{"key":"ref40","article-title":"ChatGPT becomes fastest growing app in the world, records 100mn users in 2 month","author":"Saini","year":"2023","journal-title":"LiveMint."},{"key":"ref41","volume-title":"Introducing stack overflow","author":"Spolsky","year":"2008"},{"key":"ref42","doi-asserted-by":"publisher","first-page":"17","DOI":"10.55529\/ijitc.31.17.22","article-title":"Use chat GPT to solve programming bugs","volume":"3","author":"Surameery","year":"2023","journal-title":"Int J Info Technol Comp Eng (IJITC)"},{"key":"ref43","doi-asserted-by":"publisher","first-page":"656","DOI":"10.3390\/educsci14060656","article-title":"ChatGPT: the end of online exam integrity?","volume":"14","author":"Susnjak","year":"2024","journal-title":"Educ. Sci."},{"key":"ref44","doi-asserted-by":"publisher","first-page":"235933","DOI":"10.3389\/fpsyg.2017.01454","article-title":"The influences of emotion on learning and memory","volume":"8","author":"Tyng","year":"2017","journal-title":"Front. Psychol."},{"key":"ref45","doi-asserted-by":"publisher","first-page":"485","DOI":"10.1037\/a0026609","article-title":"Emotional design in multimedia learning","volume":"104","author":"Um","year":"2012","journal-title":"J. Educ. Psychol."},{"key":"ref46","doi-asserted-by":"publisher","first-page":"814","DOI":"10.1080\/09588221.2022.2056203","article-title":"Learners\u2019 perceived AI presences in AI-supported language learning: a study of AI as a humanized agent from community of inquiry","volume":"37","author":"Wang","year":"2024","journal-title":"Comput. Assist. Lang. Learn."},{"key":"ref47","unstructured":"Malwarebytes\n            \n          \n          \n          2023"},{"key":"ref48","author":"Zhao","year":"2024"}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2024.1393903\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,16]],"date-time":"2024-09-16T01:11:00Z","timestamp":1726449060000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2024.1393903\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,16]]},"references-count":48,"alternative-id":["10.3389\/frai.2024.1393903"],"URL":"https:\/\/doi.org\/10.3389\/frai.2024.1393903","relation":{},"ISSN":["2624-8212"],"issn-type":[{"value":"2624-8212","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,9,16]]},"article-number":"1393903"}}