• 文献检索
  • 文档翻译
  • 深度研究
  • 学术资讯
  • Suppr Zotero 插件Zotero 插件
  • 邀请有礼
  • 套餐&价格
  • 历史记录
应用&插件
Suppr Zotero 插件Zotero 插件浏览器插件Mac 客户端Windows 客户端微信小程序
定价
高级版会员购买积分包购买API积分包
服务
文献检索文档翻译深度研究API 文档MCP 服务
关于我们
关于 Suppr公司介绍联系我们用户协议隐私条款
关注我们

Suppr 超能文献

核心技术专利：CN118964589B侵权必究
粤ICP备2023148730 号-1Suppr @ 2026

文献检索

告别复杂PubMed语法，用中文像聊天一样搜索，搜遍4000万医学文献。AI智能推荐，让科研检索更轻松。

立即免费搜索

文件翻译

保留排版，准确专业，支持PDF/Word/PPT等文件格式，支持 12+语言互译。

免费翻译文档

深度研究

AI帮你快速写综述，25分钟生成高质量综述，智能提取关键信息，辅助科研写作。

立即免费体验

关于测量对大语言模型生成问卷和人工生成问卷的情感反应和感知的初步研究。

A pilot study of measuring emotional response and perception of LLM-generated questionnaire and human-generated questionnaires.

机构信息

School of Computer, Data and Mathematical Science, Western Sydney University, Sydney, Australia.

College of Information Technology, United Arab Emirates University, Al Ain, United Arab Emirates.

出版信息

Sci Rep. 2024 Feb 2;14(1):2781. doi: 10.1038/s41598-024-53255-1.

DOI:10.1038/s41598-024-53255-1
PMID:38308014
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC10837442/
Abstract

The advent of ChatGPT has sparked a heated debate surrounding natural language processing technology and AI-powered chatbots, leading to extensive research and applications across various disciplines. This pilot study aims to investigate the impact of ChatGPT on users' experiences by administering two distinct questionnaires, one generated by humans and the other by ChatGPT, along with an Emotion Detecting Model. A total of 14 participants (7 female and 7 male) aged between 18 and 35 years were recruited, resulting in the collection of 8672 ChatGPT-associated data points and 8797 human-associated data points. Data analysis was conducted using Analysis of Variance (ANOVA). The results indicate that the utilization of ChatGPT enhances participants' happiness levels and reduces their sadness levels. While no significant gender influences were observed, variations were found about specific emotions. It is important to note that the limited sample size, narrow age range, and potential cultural impacts restrict the generalizability of the findings to a broader population. Future research directions should explore the impact of incorporating additional language models or chatbots on user emotions, particularly among specific age groups such as older individuals and teenagers. As one of the pioneering works evaluating the human perception of ChatGPT text and communication, it is noteworthy that ChatGPT received positive evaluations and demonstrated effectiveness in generating extensive questionnaires.

摘要

ChatGPT 的出现引发了一场关于自然语言处理技术和人工智能聊天机器人的激烈争论，促使各个学科对其进行了广泛的研究和应用。本试点研究旨在通过使用人类和 ChatGPT 生成的两个不同问卷以及情绪检测模型，调查 ChatGPT 对用户体验的影响。共招募了 14 名年龄在 18 至 35 岁之间的参与者（7 名女性和 7 名男性），共收集了 8672 个与 ChatGPT 相关的数据点和 8797 个与人相关的数据点。使用方差分析（ANOVA）进行数据分析。结果表明，使用 ChatGPT 提高了参与者的幸福感并降低了他们的悲伤感。虽然没有观察到显著的性别影响，但在特定情绪方面存在差异。需要注意的是，样本量有限、年龄范围狭窄以及潜在的文化影响限制了研究结果在更广泛人群中的推广。未来的研究方向应该探索在用户情绪方面纳入其他语言模型或聊天机器人的影响，特别是在特定年龄群体（如老年人和青少年）中。作为评估人类对 ChatGPT 文本和交流的感知的开创性工作之一，值得注意的是，ChatGPT 获得了积极的评价，并在生成广泛的问卷方面表现出了有效性。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/2729/10837442/4ea3c0b96fbc/41598_2024_53255_Fig9_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/2729/10837442/34cbec777608/41598_2024_53255_Fig1_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/2729/10837442/15a59de24ba8/41598_2024_53255_Fig2_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/2729/10837442/07e8575034a7/41598_2024_53255_Fig3_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/2729/10837442/1ff4d39cdac3/41598_2024_53255_Fig4_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/2729/10837442/2adf0939e19b/41598_2024_53255_Fig5_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/2729/10837442/567dd8292b91/41598_2024_53255_Fig6_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/2729/10837442/51924ddc300a/41598_2024_53255_Fig7_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/2729/10837442/9300f8af3e14/41598_2024_53255_Fig8_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/2729/10837442/4ea3c0b96fbc/41598_2024_53255_Fig9_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/2729/10837442/34cbec777608/41598_2024_53255_Fig1_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/2729/10837442/15a59de24ba8/41598_2024_53255_Fig2_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/2729/10837442/07e8575034a7/41598_2024_53255_Fig3_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/2729/10837442/1ff4d39cdac3/41598_2024_53255_Fig4_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/2729/10837442/2adf0939e19b/41598_2024_53255_Fig5_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/2729/10837442/567dd8292b91/41598_2024_53255_Fig6_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/2729/10837442/51924ddc300a/41598_2024_53255_Fig7_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/2729/10837442/9300f8af3e14/41598_2024_53255_Fig8_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/2729/10837442/4ea3c0b96fbc/41598_2024_53255_Fig9_HTML.jpg

相似文献

1
A pilot study of measuring emotional response and perception of LLM-generated questionnaire and human-generated questionnaires.关于测量对大语言模型生成问卷和人工生成问卷的情感反应和感知的初步研究。
Sci Rep. 2024 Feb 2;14(1):2781. doi: 10.1038/s41598-024-53255-1.
2
Capacity of Generative AI to Interpret Human Emotions From Visual and Textual Data: Pilot Evaluation Study.生成式人工智能从视觉和文本数据中解读人类情感的能力：初步评估研究。
JMIR Ment Health. 2024 Feb 6;11:e54369. doi: 10.2196/54369.
3
The Impact of Performance Expectancy, Workload, Risk, and Satisfaction on Trust in ChatGPT: Cross-Sectional Survey Analysis.绩效预期、工作量、风险和满意度对信任 ChatGPT 的影响：横断面调查分析。
JMIR Hum Factors. 2024 May 27;11:e55399. doi: 10.2196/55399.
4
Exploring Emotion Recognition Patterns Among Iranian People Using CANTAB as an Approved Neuro-Psychological Assessment.使用CANTAB作为一种认可的神经心理学评估方法探索伊朗人群中的情绪识别模式。
Basic Clin Neurosci. 2023 Mar-Apr;14(2):289-295. doi: 10.32598/bcn.2022.3607.1. Epub 2023 Mar 1.
5
ChatGPT and large language model (LLM) chatbots: The current state of acceptability and a proposal for guidelines on utilization in academic medicine.ChatGPT 和大型语言模型 (LLM) 聊天机器人：在接受度方面的现状以及在学术医学中使用指南的建议。
J Pediatr Urol. 2023 Oct;19(5):598-604. doi: 10.1016/j.jpurol.2023.05.018. Epub 2023 Jun 2.
6
Quantification of vascular function changes under different emotion states: A pilot study.不同情绪状态下血管功能变化的量化：一项初步研究。
Technol Health Care. 2017;25(3):447-456. doi: 10.3233/THC-161284.
7
Effects of induced sad mood on facial emotion perception in young and older adults.诱导悲伤情绪对年轻人和老年人面部情绪感知的影响。
Neuropsychol Dev Cogn B Aging Neuropsychol Cogn. 2019 May;26(3):319-335. doi: 10.1080/13825585.2018.1438584. Epub 2018 Feb 15.
8
Impaired emotion perception in schizophrenia shows sex differences with channel- and category-specific effects: A pilot study.精神分裂症患者的情绪知觉受损存在性别差异，且具有通道和类别特异性：一项初步研究。
J Psychiatr Res. 2023 May;161:150-157. doi: 10.1016/j.jpsychires.2023.03.011. Epub 2023 Mar 8.
9
Investigating the Impact of User Trust on the Adoption and Use of ChatGPT: Survey Analysis.研究用户信任对 ChatGPT 采用和使用的影响：调查分析。
J Med Internet Res. 2023 Jun 14;25:e47184. doi: 10.2196/47184.
10
Turkish Emotional Word Norms for Arousal, Valence, and Discrete Emotion Categories.土耳其情绪词唤醒度、效价和离散情绪类别常模。
Psychol Rep. 2021 Feb;124(1):188-209. doi: 10.1177/0033294118814722. Epub 2018 Dec 4.

引用本文的文献

1
Digital psychiatry: concepts, framework, and implications.数字精神病学：概念、框架及影响
Front Psychiatry. 2025 Jul 4;16:1572444. doi: 10.3389/fpsyt.2025.1572444. eCollection 2025.
2
The benefits and dangers of anthropomorphic conversational agents.拟人化对话代理的益处与风险。
Proc Natl Acad Sci U S A. 2025 Jun 3;122(22):e2415898122. doi: 10.1073/pnas.2415898122. Epub 2025 May 16.
3
Evaluating the agreement between ChatGPT-4 and validated questionnaires in screening for anxiety and depression in college students: a cross-sectional study.

本文引用的文献

1
What ChatGPT and generative AI mean for science.ChatGPT和生成式人工智能对科学意味着什么。
Nature. 2023 Feb;614(7947):214-216. doi: 10.1038/d41586-023-00340-6.
2
Comparing YOLOv3, YOLOv4 and YOLOv5 for Autonomous Landing Spot Detection in Faulty UAVs.比较 YOLOv3、YOLOv4 和 YOLOv5 在无人机故障自主着陆点检测中的应用。
Sensors (Basel). 2022 Jan 8;22(2):464. doi: 10.3390/s22020464.
3
Gender differences in emotion perception and self-reported emotional intelligence: A test of the emotion sensitivity hypothesis.情绪感知与自我报告的情商中的性别差异：情绪敏感性假设的检验。
评估ChatGPT-4与经过验证的问卷在大学生焦虑和抑郁筛查中的一致性：一项横断面研究。
BMC Psychiatry. 2025 Apr 10;25(1):359. doi: 10.1186/s12888-025-06798-0.
4
A preliminary simulator study on exploring responses of drivers to driving system reminders on four stimuli in vehicles.一项关于探索驾驶员对车辆中四种刺激下驾驶系统提醒的反应的初步模拟器研究。
Sci Rep. 2025 Feb 1;15(1):4009. doi: 10.1038/s41598-025-87571-x.
5
Evaluating ChatGPT-4.0's data analytic proficiency in epidemiological studies: A comparative analysis with SAS, SPSS, and R.评估 ChatGPT-4.0 在流行病学研究中的数据分析能力：与 SAS、SPSS 和 R 的对比分析。
J Glob Health. 2024 Mar 29;14:04070. doi: 10.7189/jogh.14.04070.
PLoS One. 2018 Jan 25;13(1):e0190712. doi: 10.1371/journal.pone.0190712. eCollection 2018.
4
Gender Differences in Emotional Response: Inconsistency between Experience and Expressivity.情绪反应中的性别差异：体验与表达之间的不一致。
PLoS One. 2016 Jun 30;11(6):e0158666. doi: 10.1371/journal.pone.0158666. eCollection 2016.
5
Influence of gender in the recognition of basic facial expressions: A critical literature review.性别对面部基本表情识别的影响：文献综述。
World J Psychiatry. 2015 Sep 22;5(3):342-51. doi: 10.5498/wjp.v5.i3.342.