EnjoyEAT: Embodied Interaction for Behavior-Aware, CBT-Informed Eating-Disorder Support

Digital tools for eating-disorder support often rely on retrospective self-report or text-based prompts, offering limited support for the embodied, temporally unfolding nature of eating episodes. We introduce Embodied Therapeutic Interaction (ETI), a design framework for translating CBT-informed principles into phase-aligned, behavior-aware interactions, and instantiate it in EnjoyEAT, a prototype combining surface electromyography sensing with pre-meal preparation, in-meal awareness cues, and post-meal reflection. Formative inquiry with experts and people with lived experience yielded requirements concerning temporal vulnerability, bodily awareness, emotional safety, and autonomy-preserving feedback. A four-week, uncontrolled in-the-wild study with 12 participants reporting subclinical tendencies showed decreased EDE-Q scores and positive user-experience ratings. Interviews indicated feedback helped some participants notice and reflect on eating patterns, while revealing tensions around sensing accuracy, setup burden, and sustained engagement. Though not a clinical intervention, EnjoyEAT offers HCI design evidence about phase alignment, soft embodiment, reflective mediation, and emotionally careful feedback for situated recovery support.

Authors

Institutions

Publication Details

Journal
International Journal of Human-Computer Interaction
Published
2026-10-15
DOI
https://doi.org/10.1080/10447318.2026.2740424
Primary Topic
Innovative Human-Technology Interaction
Type
article
Field-Weighted Citation Impact
0.00

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

EnjoyEAT: Embodied Interaction for Behavior-Aware, CBT-Informed Eating-Disorder Support

Danni Chang, Yilin Jiang, Luyao Wang, Mengge Liu
International Journal of Human-Computer Interaction
Innovative Human-Technology Interaction
article

EnjoyEAT: Embodied Interaction for Behavior-Aware, CBT-Informed Eating-Disorder Support

Danni Chang, Yilin Jiang, Luyao Wang, Mengge Liu
article en

Abstract

Digital tools for eating-disorder support often rely on retrospective self-report or text-based prompts, offering limited support for the embodied, temporally unfolding nature of eating episodes. We introduce Embodied Therapeutic Interaction (ETI), a design framework for translating CBT-informed principles into phase-aligned, behavior-aware interactions, and instantiate it in EnjoyEAT, a prototype combining surface electromyography sensing with pre-meal preparation, in-meal awareness cues, and post-meal reflection. Formative inquiry with experts and people with lived experience yielded requirements concerning temporal vulnerability, bodily awareness, emotional safety, and autonomy-preserving feedback. A four-week, uncontrolled in-the-wild study with 12 participants reporting subclinical tendencies showed decreased EDE-Q scores and positive user-experience ratings. Interviews indicated feedback helped some participants notice and reflect on eating patterns, while revealing tensions around sensing accuracy, setup burden, and sustained engagement. Though not a clinical intervention, EnjoyEAT offers HCI design evidence about phase alignment, soft embodiment, reflective mediation, and emotionally careful feedback for situated recovery support.

International Journal of Human-Computer Interaction
Nanyang Technological University (SG), Shanghai Jiao Tong University (CN)
Shanghai Office of Philosophy and Social Science
Good health and well-being
Openalex Percentile: Top 9%
Innovative Human-Technology Interaction
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.