Emotionally Aware AI Chatbots for Adolescents: A Review of Psychological Principles for Learning, Calibrated Trust, and Healthy Human–AI Interaction

Conversational artificial intelligence now belongs to ordinary adolescent life, but the psychological research that should guide its design spreads over fields which seldom cite each other. Research on adolescent development, on misinformation susceptibility, on trust in automation, on chatbot-supported learning and on companion-chatbot overreliance has grown up separately, and each of these areas answers only part of the question of how a general-purpose chatbot should talk to a teenager. This paper brings together twenty-one sources from developmental psychology, human factors, human-computer interaction and educational technology, in order to show what is now known about adolescent chatbot interaction and what this means for conversational design. Three results appear repeatedly in this research. First, adolescence is a design context of its own, not a smaller version of adulthood, since reward sensitivity, social influence and emotional regulation are still developing, while exposure to persuasive conversational systems has already reached almost everyone. Second, trust in a chatbot changes behavior in ways that can be measured; thus, the proper design target is calibrated trust rather than maximal trust. Third, the failure modes that matter most for adolescent users, that is, hallucination, sycophancy and unwarranted confidence, originate in the model; the user is not their source. From these results this paper consolidates ten conversational design principles into four clusters, namely epistemic calibration, metacognitive scaffolding, bounded emotional support and autonomy preservation. The framework here is a conceptual synthesis and puts forward testable predictions, but it has not been empirically validated.

Authors

Publication Details

Journal
Journal of Education Humanities and Social Sciences
Published
2026-11-16
DOI
https://doi.org/10.54097/kv51qy58
Primary Topic
Social Robot Interaction and HRI
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Emotionally Aware AI Chatbots for Adolescents: A Review of Psychological Principles for Learning, Calibrated Trust, and Healthy Human–AI Interaction

Linxi Chen
1 links
Journal of Education Humanities and Social Sciences
Social Robot Interaction and HRI
article

Emotionally Aware AI Chatbots for Adolescents: A Review of Psychological Principles for Learning, Calibrated Trust, and Healthy Human–AI Interaction

Linxi Chen
article en

Abstract

Conversational artificial intelligence now belongs to ordinary adolescent life, but the psychological research that should guide its design spreads over fields which seldom cite each other. Research on adolescent development, on misinformation susceptibility, on trust in automation, on chatbot-supported learning and on companion-chatbot overreliance has grown up separately, and each of these areas answers only part of the question of how a general-purpose chatbot should talk to a teenager. This paper brings together twenty-one sources from developmental psychology, human factors, human-computer interaction and educational technology, in order to show what is now known about adolescent chatbot interaction and what this means for conversational design. Three results appear repeatedly in this research. First, adolescence is a design context of its own, not a smaller version of adulthood, since reward sensitivity, social influence and emotional regulation are still developing, while exposure to persuasive conversational systems has already reached almost everyone. Second, trust in a chatbot changes behavior in ways that can be measured; thus, the proper design target is calibrated trust rather than maximal trust. Third, the failure modes that matter most for adolescent users, that is, hallucination, sycophancy and unwarranted confidence, originate in the model; the user is not their source. From these results this paper consolidates ten conversational design principles into four clusters, namely epistemic calibration, metacognitive scaffolding, bounded emotional support and autonomy preservation. The framework here is a conceptual synthesis and puts forward testable predictions, but it has not been empirically validated.

Journal of Education Humanities and Social SciencesVol. 65
Social Robot Interaction and HRI
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon