Exploring Affective Representations in Emotional Narratives: An Exploratory Study Comparing ChatGPT and Human Responses.

IF 4.2 2区 心理学 Q1 PSYCHOLOGY, SOCIAL Cyberpsychology, behavior and social networking Pub Date : 2024-09-04 DOI:10.1089/cyber.2024.0100
Chaery Park, Jongwan Kim
{"title":"Exploring Affective Representations in Emotional Narratives: An Exploratory Study Comparing ChatGPT and Human Responses.","authors":"Chaery Park, Jongwan Kim","doi":"10.1089/cyber.2024.0100","DOIUrl":null,"url":null,"abstract":"<p><p>While artificial Intelligence (AI) has made significant advancements, the seeming absence of its emotional ability has hindered effective communication with humans. This study explores how ChatGPT (ChatGPT-3.5 Mar 23, 2023 Version) represents affective responses to emotional narratives and compare these responses to human responses. Thirty-four participants read affect-eliciting short stories and rated their emotional responses and 10 recorded ChatGPT sessions generated responses to the stories. Classification analyses revealed the successful identification of affective categories of stories, valence, and arousal within and across sessions for ChatGPT. Classification analyses revealed the successful identification of affective categories of stories, valence, and arousal within and across sessions for ChatGPT. Classification accuracies predicting affective categories of stories, valence, and arousal of humans based on the affective ratings of ChatGPT and vice versa were not significant, indicating differences in the way the affective states were represented., indicating differences in the way the affective states were represented. These findings suggested that ChatGPT can distinguish emotional states and generate affective responses consistently, but there are differences in how the affective states are represented between ChatGPT and humans. Understanding these mechanisms is crucial for improving emotional interactions with AI.</p>","PeriodicalId":10872,"journal":{"name":"Cyberpsychology, behavior and social networking","volume":null,"pages":null},"PeriodicalIF":4.2000,"publicationDate":"2024-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Cyberpsychology, behavior and social networking","FirstCategoryId":"102","ListUrlMain":"https://doi.org/10.1089/cyber.2024.0100","RegionNum":2,"RegionCategory":"心理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"PSYCHOLOGY, SOCIAL","Score":null,"Total":0}
引用次数: 0

Abstract

While artificial Intelligence (AI) has made significant advancements, the seeming absence of its emotional ability has hindered effective communication with humans. This study explores how ChatGPT (ChatGPT-3.5 Mar 23, 2023 Version) represents affective responses to emotional narratives and compare these responses to human responses. Thirty-four participants read affect-eliciting short stories and rated their emotional responses and 10 recorded ChatGPT sessions generated responses to the stories. Classification analyses revealed the successful identification of affective categories of stories, valence, and arousal within and across sessions for ChatGPT. Classification analyses revealed the successful identification of affective categories of stories, valence, and arousal within and across sessions for ChatGPT. Classification accuracies predicting affective categories of stories, valence, and arousal of humans based on the affective ratings of ChatGPT and vice versa were not significant, indicating differences in the way the affective states were represented., indicating differences in the way the affective states were represented. These findings suggested that ChatGPT can distinguish emotional states and generate affective responses consistently, but there are differences in how the affective states are represented between ChatGPT and humans. Understanding these mechanisms is crucial for improving emotional interactions with AI.

查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
探索情感叙述中的情感表征:比较 ChatGPT 和人类反应的探索性研究。
虽然人工智能(AI)取得了长足的进步,但其情感能力的缺失似乎阻碍了与人类的有效交流。本研究探讨了 ChatGPT(ChatGPT-3.5 2023 年 3 月 23 日版)如何表现对情感叙述的情感反应,并将这些反应与人类的反应进行比较。34 名参与者阅读了诱发情感的短篇故事,并对他们的情感反应进行了评分,10 个录制的 ChatGPT 会话生成了对故事的反应。分类分析表明,在 ChatGPT 的会话中和跨会话中,成功识别了故事的情感类别、情绪和唤醒。分类分析表明,在 ChatGPT 中,成功识别出了故事的情感类别、情绪和唤醒,并在不同的会话中识别出了不同的情感类别。根据 ChatGPT 的情感评级预测人类故事的情感类别、情感价位和唤醒程度的分类准确率不显著,反之亦然,这表明情感状态的表现方式存在差异。这些发现表明,ChatGPT 可以区分情感状态并产生一致的情感反应,但 ChatGPT 和人类在情感状态的表现方式上存在差异。了解这些机制对于改善与人工智能的情感互动至关重要。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
CiteScore
9.60
自引率
3.00%
发文量
123
期刊介绍: Cyberpsychology, Behavior, and Social Networking is a leading peer-reviewed journal that is recognized for its authoritative research on the social, behavioral, and psychological impacts of contemporary social networking practices. The journal covers a wide range of platforms, including Twitter, Facebook, internet gaming, and e-commerce, and examines how these digital environments shape human interaction and societal norms. For over two decades, this journal has been a pioneering voice in the exploration of social networking and virtual reality, establishing itself as an indispensable resource for professionals and academics in the field. It is particularly celebrated for its swift dissemination of findings through rapid communication articles, alongside comprehensive, in-depth studies that delve into the multifaceted effects of interactive technologies on both individual behavior and broader societal trends. The journal's scope encompasses the full spectrum of impacts—highlighting not only the potential benefits but also the challenges that arise as a result of these technologies. By providing a platform for rigorous research and critical discussions, it fosters a deeper understanding of the complex interplay between technology and human behavior.
期刊最新文献
Harnessing Hope in Digital Spaces for Health Equity: How Group Comparison Information and Supportive Comments Influence Bone Marrow Donor Intentions for African Americans. Assessing Bias Toward a Black or White Simulated Patient with Obesity in a Virtual Reality-Based Genomics Encounter. Unmasking Deception: Strategies to Combat AI-Driven Disinformation. Virtual Reality Tennis Training: Performance Gains Derived from User Characteristics. Exploring Alternative Health Facebook Groups in the COVID-19 Pandemic: An Automated Content Analysis Through Structural Topic Modeling.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1