Decoding dynamic emotional valence in GenAI interactions: insights from covariate-dependent Markov chains
Frontiers in Psychology · 11.05.2026 · 17
DOI: 10.3389/fpsyg.2026.1783364 ↗Kurz gefasst
Fachartikel in der Zeitschrift Frontiers in Psychology, online erschienen am 11.05.2026. Verfasst von Yiming Taclis Luo und 3 weiteren Autor:innen. Beteiligte Einrichtung: Faculty of Applied Sciences, Macao Polytechnic University, Macao, China. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 59 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Introduction
User affective valence states evolve dynamically during human–GenAI interaction, yet existing research provides limited insight into how the quality of AI outputs is associated with these moment-to-moment emotional valence transitions.
Objective
This study aims to fill this gap by proposing a covariate-dependent Markov chain model to examine how the quality of AI responses is associated with transitions in user emotional valence.
Methods
We conducted an experiment on AI-assisted academic writing for university students and analyzed 886 interaction sequences.
Results
The results show a significant polarization effect of AI response quality on user emotional valence state transitions: high-quality responses stabilize and reinforce positive emotional valence, while low-quality responses tend to trigger emotional deterioration. Furthermore, group differences based on emotional stability are also analyzed.
Discussion
This research provides a new perspective for understanding emotional dynamics in human–computer dialogues and offers practical evidence for building emotionally adaptive GenAI systems.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Faculty of Applied Sciences, Macao Polytechnic University, Macao, China.
Zitieren
APA
Luo, Y. T., Liu, T., Pang, P., & Kan, H. Y. (2026). Decoding dynamic emotional valence in GenAI interactions: insights from covariate-dependent Markov chains. Frontiers in Psychology, 17. https://doi.org/10.3389/fpsyg.2026.1783364
Vancouver
Luo YT, Liu T, Pang P, Kan HY. Decoding dynamic emotional valence in GenAI interactions: insights from covariate-dependent Markov chains. Frontiers in Psychology. 2026;17. doi:10.3389/fpsyg.2026.1783364
BibTeX
@article{Luo2026,
author = {Luo, Yiming Taclis and Liu, Ting and Pang, Patrick and Kan, Ho Yin},
title = {Decoding dynamic emotional valence in GenAI interactions: insights from covariate-dependent Markov chains},
journal = {Frontiers in Psychology},
year = {2026},
volume = {17},
doi = {10.3389/fpsyg.2026.1783364}
}
EUVIMED