Skip to main content

ETHNOS_APP

Home • Search • Journals • List 0

Exploring Affective Representations in Emotional Narratives

An Exploratory Study Comparing ChatGPT and Human Responses

Bibliographic Data

ID22004362
AuthorsChaery Park (Jeonbuk National University), Jongwan Kim (0000-0003-1316-1041, Jeonbuk National University, corresponding author)
Year2024
Volume27
Issue10
Pages736-741
Publication date2024-10-01
Peer ReviewedYes
Open AccessYes
TypeARTICLE
VenueCyberpsychology Behavior and Social Networking (JOURNAL)
Journal identifiersISSN: 2152-2715 • E-ISSN: 2152-2723
PublisherSAGE Publications (PUBLISHER • US)
DOI10.1089/cyber.2024.0100
PMID39229675
OpenAlexW4402238373
LanguageEN
Citations received3
References cited20

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

Art · Cognitive psychology · Developmental psychology · Exploratory research · Medical emergency · Narrative · Poison control · Sociology · Human Factors and Ergonomics · Medicine · Mental Health Research Topics · Mental Health via Writing · Misinformation and Its Impacts · Psychology · Social Psychology

  • Can ChatGPT rate body-related images like humans? Effects of temperature and few-shot prompting on valence and arousal judgments

    Open Access•Yueyang Xiao, Sanle Zhao et al.•Body Image•2026

  • Generative artificial intelligence perspectives on typical landscape types

    Open Access•Jinxuan Liu, Tianci Zhang et al.•Landscape and Urban Planning•2025

  • Human-written vs. ChatGPT-generated texts

    Open Access•Man Zhang, Jiawei Zhang•System•2025

  • The Levels of Emotional Awareness Scale

    Richard D Lane, Donald M Quinlan et al.•Journal of Personality Assessment•1990

  • Can AI language models replace human participants?

    Open Access•Danica Dillion, Niket Tandon et al.•Trends in Cognitive Sciences•2023

  • G*Power 3

    Open Access•Franz Faul, Edgar Erdfelder et al.•Behavior Research Methods•2007

  • Taste the music

    Open Access•Chaery Park, Jongwan Kim•Cognition•2024

Unique citing works3
Citations per year3
Citation span2025 - 2026 (2)
Citation velocitycurrent
Highly citedNo
Citation typesNeutral: 3

Tools

Open DOI
Ethnos_APP • Open Source Project • MIT License • Frontend v2.0.0 • Privacy and Cookies • API Documentation: api.ethnos.app/docs • API Source Code: GitHub • DOI: 10.5281/zenodo.17049435 • Frontend Source Code: GitHub • DOI: 10.5281/zenodo.17050053 • cruz.rio.br • Expectantes Misericordiae