arxiv: 2604.08114 · v1 · submitted 2026-04-09 · 💻 cs.HC

StoryEcho: A Generative Child-as-Actor Storytelling System for Picky-Eating Intervention

Yanuo Zhou , Jun Fang , Yuntao Wang , Yi Wang , Nan Gao , Jinlei Liu , Yuanchun Shi This is my paper

Pith reviewed 2026-05-10 17:25 UTC · model grok-4.3

classification 💻 cs.HC

keywords picky eatinggenerative storytellingchild-as-actorhome-based interventionfamily routinespreschool childrenbehavior supportinteractive narratives

0 comments p. Extension

The pith

A generative system in which children act as persistent characters in stories that update based on their real eating behavior can raise willingness to try low-preference foods.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper seeks to establish that children can be positioned as active participants in ongoing personalized stories that extend beyond single meals, with narratives adapting through lightweight feedback on actual food-related actions. This approach matters because picky eating restricts dietary variety and generates repeated family tension during feeding. A formative study with caregivers and teachers informed design considerations, leading to iterative development and a between-group field trial with 11 families. The work tests whether non-mealtime story engagement combined with behavior-informed updates can shift children's approach to target foods and ease parental pressure in everyday routines.

Core claim

StoryEcho is a generative storytelling system in which the child appears as a persistent character in personalized tales; after meals, simple feedback on interactions with target foods informs story updates so that narrative developments reflect and reinforce positive real-world behavior, supporting repeated intervention across family routines rather than isolated mealtimes.

What carries the argument

Generative child-as-actor storytelling, which places the child as a recurring protagonist whose story arcs evolve through post-meal feedback loops to encourage repeated engagement with low-preference foods outside direct mealtime pressure.

If this is right

Behavior support can unfold through recurring non-mealtime story engagement instead of direct food-centered prompts during meals.
Lightweight feedback mechanisms allow stories to adapt to individual child actions without requiring constant adult oversight.
Stakeholder-informed iterative design produces systems that fit existing family routines and gain acceptance from both children and caregivers.
Preliminary field results indicate measurable shifts in children's food-related actions alongside reduced family tension around feeding.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

The same child-as-actor update loop could be tested for other recurring home behaviors such as bedtime or hygiene routines.
Over longer periods the approach might sustain engagement better than one-off interventions if story novelty is managed through new plot branches.
Combining the system with automated sensing of food intake could strengthen the accuracy of behavior-to-story mapping without added parental burden.

Load-bearing premise

Observed increases in children's willingness to approach foods and decreases in parental pressure are caused by the StoryEcho system itself rather than novelty of the technology, parental expectations, or the limited sample size in the field study.

What would settle it

A larger controlled study that matches groups for novelty exposure and measures food approach behaviors after several weeks, finding no significant difference between StoryEcho families and control families.

Figures

Figures reproduced from arXiv: 2604.08114 by Jinlei Liu, Jun Fang, Nan Gao, Yanuo Zhou, Yi Wang, Yuanchun Shi, Yuntao Wang.

**Figure 1.** Figure 1: StoryEcho as an interactive generative child-as-actor storytelling loop across family routines. Outside mealtimes, [PITH_FULL_IMAGE:figures/full_fig_p003_1.png] view at source ↗

**Figure 2.** Figure 2: Boxplots of the five session-level measures: [PITH_FULL_IMAGE:figures/full_fig_p009_2.png] view at source ↗

**Figure 3.** Figure 3: Overview of StoryEcho’s system-level design. The loop begins with avatar creation (a) and story generation (b), [PITH_FULL_IMAGE:figures/full_fig_p020_3.png] view at source ↗

**Figure 4.** Figure 4: Detailed workflow of StoryEcho’s generative storytelling content design. (A) The story framework module combines [PITH_FULL_IMAGE:figures/full_fig_p020_4.png] view at source ↗

read the original abstract

Picky eating in children can undermine dietary diversity and the development of healthy eating habits, while also creating recurring tension in family feeding routines. Prior interventions have explored food-centered designs, enhanced utensils, and mealtime interactive systems, but few position children as active participants in intervention processes that extend beyond single mealtime interactions. To better understand everyday responses to picky eating and child-acceptable intervention mechanisms, we conducted a formative study with caregivers and kindergarten teachers. Based on the resulting design considerations and iterative stakeholder review, we designed StoryEcho, a generative child-as-actor storytelling system for picky eating intervention. StoryEcho engages children outside mealtimes through personalized stories in which the child appears as a persistent story character and later shapes story development through real-world food-related behavior. The system combines non-mealtime story engagement, lightweight post-meal feedback, and behavior-informed story updates to support repeated intervention across everyday family routines. We evaluated StoryEcho in a between-group field study with 11 families of preschool children. Results provide preliminary evidence that StoryEcho can significantly increase children's willingness to approach and try target low-preference foods while reducing parental pressure around feeding. These findings suggest the promise of generative child-as-actor storytelling as a design approach for home-based behavior support that unfolds through recurring family routines.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Desk Editor's Note private letter to a colleague

StoryEcho puts kids as persistent heroes in generative stories that update from real eating behavior, with a tiny field study showing some uptake in food willingness.

read the letter

The main point is a system that creates ongoing stories with the child as the main character, then tweaks the plot based on post-meal reports from parents. This runs outside mealtimes and aims to build habits through repeated family routines rather than direct food pressure. They grounded the design in a formative study with caregivers and kindergarten teachers, then iterated with stakeholder feedback before the field test. That process gives the work a practical feel and avoids purely tech-driven ideas. The between-group deployment with 11 families produced reported gains in kids approaching low-preference foods and drops in parental feeding pressure, which aligns with the stated goals. The persistent character and behavior-to-story loop is the clearest step beyond earlier mealtime gadgets or one-shot apps. The evaluation section is the clear limitation. Eleven families total leaves the between-group comparison underpowered, and the abstract gives no numbers on randomization, group sizes, baselines, or statistical tests. Without those, novelty effects or parent expectations could explain the shifts as easily as the specific storytelling mechanics. The claim of significant change therefore stays preliminary. This is useful reading for HCI researchers who build generative tools for child behavior or family health routines. Design-oriented readers will get concrete examples of how to fold real-world feedback into interactive stories. It is worth sending to peer review so the methods can be examined and the design ideas can be tested against related work in more detail.

Referee Report

2 major / 2 minor

Summary. The paper introduces StoryEcho, a generative storytelling system that positions children as persistent characters in personalized stories updated by their real-world food behaviors, intended to support picky-eating interventions outside mealtimes. It reports a formative study with caregivers and teachers leading to design considerations, followed by iterative development and a between-group field study with 11 families of preschool children. The central empirical claim is that StoryEcho produces preliminary evidence of significantly increased child willingness to approach and try target low-preference foods together with reduced parental feeding pressure.

Significance. If the reported effects prove robust under stronger controls, the work offers a novel HCI contribution by extending food-related interventions beyond single mealtimes into recurring, child-driven generative narratives. The child-as-actor mechanism combined with lightweight behavior feedback represents a distinct design pattern for home-based behavior support that could inform future systems in child health and family routines.

major comments (2)

[Abstract and Evaluation] Abstract and Evaluation section: The between-group field study is reported with n=11 families and claims 'significant' increases in willingness to try foods and reductions in parental pressure, yet no statistical methods, effect sizes, p-values, power analysis, randomization procedure, baseline equivalence checks, or exclusion criteria are described. This absence directly weakens the ability to assess whether the data support the central claim of preliminary evidence.
[Evaluation] Evaluation section: The design does not mention blinding, placebo controls, or explicit measures to isolate the contribution of StoryEcho's specific features (persistent child character and behavior-informed story updates) from confounds such as novelty effects, parental expectations, or demand characteristics. With a small between-group sample, these omissions leave causal attribution insecure and constitute a load-bearing limitation for the reported outcomes.

minor comments (2)

[Abstract] Abstract: The sentence reporting results could explicitly restate the sample size (n=11) to give readers immediate context for the strength of the preliminary evidence.
[Discussion] The manuscript would benefit from a dedicated limitations subsection that directly addresses the small sample and potential confounds rather than leaving them implicit.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for their constructive and detailed feedback. We have revised the manuscript to improve transparency in the reporting of our evaluation and to more explicitly address the limitations of the study design. Our point-by-point responses follow.

read point-by-point responses

Referee: [Abstract and Evaluation] Abstract and Evaluation section: The between-group field study is reported with n=11 families and claims 'significant' increases in willingness to try foods and reductions in parental pressure, yet no statistical methods, effect sizes, p-values, power analysis, randomization procedure, baseline equivalence checks, or exclusion criteria are described. This absence directly weakens the ability to assess whether the data support the central claim of preliminary evidence.

Authors: We agree that the original manuscript did not provide sufficient detail on the statistical procedures, which limits readers' ability to evaluate the strength of the reported effects. In the revised manuscript we have added a dedicated Data Analysis subsection within the Evaluation section. This subsection now reports the specific statistical tests performed, all p-values, effect sizes, a post-hoc power analysis, the randomization procedure used to assign families to conditions, baseline equivalence checks across groups on key demographic and pre-study measures, and confirmation that no exclusion criteria were applied. These additions directly address the gaps identified and allow a clearer assessment of the preliminary evidence. revision: yes
Referee: [Evaluation] Evaluation section: The design does not mention blinding, placebo controls, or explicit measures to isolate the contribution of StoryEcho's specific features (persistent child character and behavior-informed story updates) from confounds such as novelty effects, parental expectations, or demand characteristics. With a small between-group sample, these omissions leave causal attribution insecure and constitute a load-bearing limitation for the reported outcomes.

Authors: We acknowledge that the field study did not employ blinding or placebo controls and did not include dedicated measures to isolate the unique contributions of the persistent child character and behavior-informed updates from broader confounds. Such controls are challenging to implement in naturalistic home settings with young children and involved parents. In the revised manuscript we have added an expanded Limitations subsection that explicitly discusses these issues, including potential novelty effects, parental expectations, and demand characteristics. The subsection also notes that the current between-group comparison offers preliminary evidence rather than definitive causal isolation of individual design features and outlines directions for future work with additional control conditions. This revision clarifies the scope and boundaries of our claims. revision: partial

Circularity Check

0 steps flagged

No significant circularity: empirical HCI design and evaluation study

full rationale

The paper describes a formative study, iterative design of the StoryEcho system, and a between-group field evaluation with 11 families. No mathematical derivations, equations, fitted parameters, model predictions, or self-citation chains appear in the claimed results. The central claim rests on observed behavioral outcomes from the field study rather than any self-referential definitions or reductions of predictions to inputs by construction. This is a standard empirical design paper whose evidence chain is independent of the patterns that would trigger circularity flags.

Axiom & Free-Parameter Ledger

0 free parameters · 2 axioms · 1 invented entities

The central claim rests on assumptions about how children engage with self-referential stories and how feedback translates into behavior change, without independent evidence provided beyond the study itself.

axioms (2)

domain assumption Children will engage with and be motivated by personalized stories in which they appear as persistent characters.
Invoked in the design of the child-as-actor mechanism and story updates.
domain assumption Lightweight post-meal feedback from parents can reliably inform story updates that reinforce positive eating behaviors.
Core to the system's repeated intervention cycle across family routines.

invented entities (1)

StoryEcho generative storytelling system no independent evidence
purpose: To deliver ongoing picky-eating intervention through child-as-actor stories updated by real-world behavior.
The novel artifact created and evaluated in the paper.

pith-pipeline@v0.9.0 · 5546 in / 1424 out tokens · 42086 ms · 2026-05-10T17:25:50.237080+00:00 · methodology

discussion (0)

Reference graph

Works this paper leans on

78 extracted references · 78 canonical work pages · 1 internal anchor

[1]

1990.Parenting stress index-short form

Richard R Abidin. 1990.Parenting stress index-short form. Vol. 118. Pediatric psychology press Charlottesville, VA

work page 1990
[2]

Cátia Braga-Pontes, Sara Simões-Dias, Marlene Lages, Maria P Guarino, and Pedro Graça. 2022. Nutrition education strategies to promote vegetable consumption in preschool children: the Veggies4myHeart project.Public Health Nutrition25, 4 (2022), 1061–1070

work page 2022
[3]

Virginia Braun and Victoria Clarke. 2006. Using thematic analysis in psychology. Qualitative research in psychology3, 2 (2006), 77–101

work page 2006
[4]

John Brooke et al. 1996. SUS-A quick and dirty usability scale.Usability evaluation in industry189, 194 (1996), 4–7

work page 1996
[5]

Stephanie P Brooks, Gabrielle L Zimmermann, Michael Lang, Shannon D Scott, Denise Thomson, Gil Wilkes, and Lisa Hartling. 2022. A framework to guide sto- rytelling as a knowledge translation intervention for health-promoting behaviour change.Implementation Science Communications3, 1 (2022), 35

work page 2022
[6]

Zhenyao Cai, Ariel Han, Xiaofei Zhou, Eva Durall Gazulla, and Kylie Peppler

work page
[7]

Child-AI Co-Creation: A Review of the Current Research Landscape and a Proposal for Six Design Considerations.Proceedings of the 24th Interaction Design and Children(2025), 916–922

work page 2025
[8]

Jiaju Chen, Minglong Tang, Yuxuan Lu, Bingsheng Yao, Elissa Fan, Xiaojuan Ma, Ying Xu, Dakuo Wang, Yuling Sun, and Liang He. 2025. Characterizing llm-empowered personalized story reading and interaction for children: Insights from multi-stakeholder perspectives. InProceedings of the 2025 CHI Conference on Human Factors in Computing Systems. 1–24

work page 2025
[9]

Liuqing Chen, Yaxuan Song, Ke Lyu, Shuhong Xiao, Yilang Shen, and Lingyun Sun. 2025. SCENIC: A Location-based System to Foster Cognitive Development in Children During Car Rides. InProceedings of the 38th Annual ACM Symposium on User Interface Software and Technology. 1–18

work page 2025
[10]

Yang Chen and Ching Chiuan Yen. 2024. More Than Just Limits: How Technol- ogy Can Support Parents in Regulating Children’s Eating Behaviors at Family Mealtimes. InExtended Abstracts of the CHI Conference on Human Factors in Computing Systems. 1–8

work page 2024
[11]

Laine Chilman, Ann Kennedy-Behr, Thuy Frakking, Libby Swanepoel, and Michele Verdonck. 2021. Picky eating in children: A scoping review to examine its intrinsic and extrinsic features and how they relate to identification.International journal of environmental research and public health18, 17 (2021), 9067

work page 2021
[12]

Jennifer Coe, Lorenzo Manera, and Erik C Fooladi. 2024. Exploring the senses of taste with young children: Multisensory discoveries of food.Food and Foodways 32, 1 (2024), 7–34

work page 2024
[13]

Natasha Chong Cole, Ruopeng An, Soo-Yeun Lee, and Sharon M Donovan. 2017. Correlates of picky eating and food neophobia in young children: a systematic review and meta-analysis.Nutrition reviews75, 7 (2017), 516–532

work page 2017
[14]

Natasha Chong Cole, Salma M Musaad, Soo-Yeun Lee, Sharon M Donovan, and The STRONG Kids Team. 2018. Home feeding environment and picky eating behavior in preschool-aged children: A prospective analysis.Eating behaviors30 (2018), 76–82

work page 2018
[15]

Lucy Cooke. 2007. The importance of exposure for healthy eating in childhood: a review.Journal of human nutrition and dietetics20, 4 (2007), 294–301

work page 2007
[16]

Alexandra Costa and Andreia Oliveira. 2023. Parental feeding practices and chil- dren’s eating behaviours: an overview of their complex relationship. InHealthcare, Vol. 11. MDPI, 400

work page 2023
[17]

Carmen Del Campo, Cristina Bouzas, and Josep A Tur. 2024. Risk Factors and consequences of food neophobia and pickiness in children and adolescents: a systematic review.Foods14, 1 (2024), 69

work page 2024
[18]

Feike Dietz. 2019. Mediated education in early modern travel stories: How travel stories contribute to children’s empirical learning.Science in Context32, 2 (2019), 193–212

work page 2019
[19]

Terence M Dovey, Paul A Staples, E Leigh Gibson, and Jason CG Halford. 2008. Food neophobia and ‘picky/fussy’eating in children: a review.Appetite50, 2-3 (2008), 181–193

work page 2008
[20]

Hasan Shahid Ferdous, Bernd Ploderer, Hilary Davis, Frank Vetere, and Kenton O’Hara. 2015. Pairing technology and meals: A contextual enquiry in the family household. InProceedings of the annual meeting of the australian special interest group for computer human interaction. 370–379

work page 2015
[21]

Lori A Francis and Leann L Birch. 2006. Does eating during television viewing affect preschool children’s intake?Journal of the American Dietetic Association 106, 4 (2006), 598–600

work page 2006
[22]

Lisa R Fries and Klazine Van der Horst. 2019. Parental Feeding Practices and As- sociations with Children’s Food Acceptance and Picky Eating.. InNestle Nutrition Conference acronym ’XX, June 03–05, 2018, Woodstock, NY Zhou et al. Institute Workshop Series, Vol. 91. 31–39

work page 2019
[23]

Franca Garzotto, Paolo Paolini, and Amalia Sabiescu. 2010. Interactive storytelling for children. InProceedings of the 9th international conference on interaction design and children. 356–359

work page 2010
[24]

Leo A Goodman. 1961. Snowball sampling.The annals of mathematical statistics (1961), 148–170

work page 1961
[25]

Melanie C Green. 2021. Transportation into narrative worlds. InEntertainment- education behind the scenes: Case studies for theory and practice. Springer, 87–101

work page 2021
[26]

Melanie C Green and Markus Appel. 2024. Narrative transportation: How stories shape how we see ourselves and the world. InAdvances in experimental social psychology. Vol. 70. Elsevier, 1–82

work page 2024
[27]

Annemarie H Hindman, Carol M Connor, Abigail M Jewkes, and Frederick J Morrison. 2008. Untangling the effects of shared book reading: Multiple factors and their associations with preschool literacy outcomes.Early Childhood Research Quarterly23, 3 (2008), 330–350

work page 2008
[28]

Alexis Hiniker, Sarita Y Schoenebeck, and Julie A Kientz. 2016. Not at the dinner table: Parents’ and children’s perspectives on family technology rules. In Proceedings of the 19th ACM conference on computer-supported cooperative work & social computing. 1376–1389

work page 2016
[29]

Ulla Hoppu, Mira Prinz, Pauliina Ojansivu, Oskar Laaksonen, and Mari A Sandell

work page
[30]

Impact of sensory-based food education in kindergarten on willingness to eat vegetables and berries.Food & Nutrition Research59, 1 (2015), 28795

work page 2015
[31]

William Huitt and John Hummel. 2003. Piaget’s theory of cognitive development. Educational psychology interactive3, 2 (2003), 1–5

work page 2003
[32]

Eunkyung Jo, Hyeonseok Bang, Myeonghan Ryu, Eun Jee Sung, Sungmook Leem, and Hwajung Hong. 2020. MAMAS: supporting parent–child mealtime interactions using automated tracking and speech recognition.Proceedings of the ACM on Human-Computer Interaction4, CSCW1 (2020), 1–32

work page 2020
[33]

Azusa Kadomura, Cheng-Yuan Li, Yen-Chang Chen, Koji Tsukada, Itiro Siio, and Hao-hua Chu. 2013. Sensing fork: Eating behavior detection utensil and mobile persuasive game. InCHI’13 Extended Abstracts on Human Factors in Computing Systems. 1551–1556

work page 2013
[34]

Huseyin Kotaman and Ali Kemal Tekin. 2019. Informational and fictional books: young children’s book preferences and teachers’ perspectives. InResearch in young children’s literacy and language development. Routledge, 302–316

work page 2019
[35]

Kennon A Lattal. 2010. Delayed reinforcement of operant behavior.Journal of the Experimental Analysis of Behavior93, 1 (2010), 129–139

work page 2010
[36]

Jungeun Lee, Kyungah Lee, Inseok Hwang, SoHyun Park, and Young-Ho Kim

work page
[37]

AutiHero: Leveraging generative AI in social narratives to engage par- ents in story-driven behavioral guidance for autistic children.arXiv preprint arXiv:2509.17608(2025)

work page internal anchor Pith review Pith/arXiv arXiv 2025
[38]

Weiwei Ma, Bo Liu, and Zhao Liu. 2021. Influence of a Video Game on Children’s Attention to Food: Should Games Be Served with a Character During Mealtime?. InInternational Conference on Human-Computer Interaction. Springer, 42–50

work page 2021
[39]

Melika Mahmoudizadeh, Mina Babashahi, Milad Rajabzadeh-Dehkordi, Mehran Nouri, and Shiva Faghih. 2025. The Interplay Between Picky Eating, Other Eating Behaviors, and Obesity Indicators in Preschool Children.Food Science & Nutrition 13, 9 (2025), e70967

work page 2025
[40]

W Stuart Millar and John S Watson. 1979. The effect of delayed feedback on infant learning reexamined.Child development(1979), 747–751

work page 1979
[41]

Kameron J Moding, Laura L Bellows, Kevin J Grimm, and Susan L Johnson. 2020. A longitudinal examination of the role of sensory exploratory behaviors in young children’s acceptance of new foods.Physiology & behavior218 (2020), 112821

work page 2020
[42]

Jessica L Montag, Michael N Jones, and Linda B Smith. 2015. The words children hear: Picture books and the statistics for language learning.Psychological science 26, 9 (2015), 1489–1496

work page 2015
[43]

Akanksha Nagarkar, Gabrielle Martin, Katherine Sadaniantz, Sanjna Iyengar, Hannah C Wisniewski, Mawulorm K Denu, Germán Chiriboga, Sarah N Forrester, Jeroan J Allison, and Lara C Kovell. 2026. Storytelling for health promotion: a scoping review.American Journal of Health Promotion40, 2 (2026), 187–209

work page 2026
[44]

Chandani Nekitsing, Pam Blundell-Birtill, Jennie E Cockroft, and Marion M Hetherington. 2019. Taste exposure increases intake and nutrition education increases willingness to try an unfamiliar vegetable in preschool children: a cluster randomized trial.Journal of the Academy of Nutrition and Dietetics119, 12 (2019), 2004–2013

work page 2019
[45]

Geoff Norman. 2010. Likert scales, levels of measurement and the “laws” of statistics.Advances in health sciences education15, 5 (2010), 625–632

work page 2010
[46]

Meghan L O’Connell, Kathryn E Henderson, Joerg Luedicke, and Marlene B Schwartz. 2012. Repeated exposure in a natural setting: A preschool intervention to increase vegetable consumption.Journal of the Academy of Nutrition and Dietetics112, 2 (2012), 230–234

work page 2012
[47]

Cliodhna O’Connor and Helene Joffe. 2020. Intercoder reliability in qualitative research: Debates and practical guidelines.International journal of qualitative methods19 (2020), 1609406919899220

work page 2020
[48]

2013.Play, dreams and imitation in childhood

Jean Piaget. 2013.Play, dreams and imitation in childhood. Routledge

work page 2013
[49]

2008.The psychology of the child

Jean Piaget and Barbel Inhelder. 2008.The psychology of the child. Basic books

work page 2008
[50]

Caroline Reverdy, Florence Chesnel, Pascal Schlich, EP Köster, and Chris Lange

work page
[51]

Appetite51, 1 (2008), 156–165

Effect of sensory education on willingness to taste novel food in children. Appetite51, 1 (2008), 156–165

work page 2008
[52]

Eric Robinson, Paul Aveyard, Amanda Daley, Kate Jolly, Amanda Lewis, Deborah Lycett, and Suzanne Higgs. 2013. Eating attentively: a systematic review and meta-analysis of the effect of food intake memory and awareness on eating.The American journal of clinical nutrition97, 4 (2013), 728–742

work page 2013
[53]

Samantha J Russell, J Jessica Wang, and Kate Cain. 2024. The influence of story character realism and theme on protagonists’ internal states and dialogue in children’s retells.Cognitive Development71 (2024), 101458

work page 2024
[54]

1997.Writing with Pictures: How To Write and Illustrate Children’s Books.ERIC

Uri Shulevitz. 1997.Writing with Pictures: How To Write and Illustrate Children’s Books.ERIC

work page 1997
[55]

Trina D Spencer and Douglas B Petersen. 2020. Narrative intervention: Principles to practice.Language, speech, and hearing services in schools51, 4 (2020), 1081– 1096

work page 2020
[56]

Silje Steinsbekk, Arielle Bonneville-Roussy, Alison Fildes, Clare H Llewellyn, and Lars Wichstrøm. 2017. Child and parent predictors of picky eating from preschool to school age.International Journal of Behavioral Nutrition and Physical Activity14, 1 (2017), 87

work page 2017
[57]

Silje Steinsbekk, Trude Hamre Sveen, Alison Fildes, Clare Llewellyn, and Lars Wichstrøm. 2017. Screening for pickiness–a validation study.International Journal of Behavioral Nutrition and Physical Activity14, 1 (2017), 2

work page 2017
[58]

Caroline M Taylor and Pauline M Emmett. 2019. Picky eating in children: causes and consequences.Proceedings of the Nutrition Society78, 2 (2019), 161–169

work page 2019
[59]

Amanda C Trofholz, Anna K Schulte, and Jerica M Berge. 2017. How parents describe picky eating and its impact on family meals: A qualitative analysis. Appetite110 (2017), 36–43

work page 2017
[60]

Frøydis N Vik, Erik Grasaas, Maaike EM Polspoel, Margrethe Røed, Elisabet R Hillesund, and Nina C Øverby. 2021. Parental phone use during mealtimes with toddlers and the associations with feeding practices and shared family meals: a cross-sectional study.BMC public health21, 1 (2021), 756

work page 2021
[61]

Guanyun Wang, Yilin Shao, Boyu Feng, Mengge Wang, Xiaojing Zhou, Yifan Yan, Zhengke Li, Yue Yang, Kuangqi Zhu, Yanan Wang, et al. 2025. Play With Morphing Food: Supporting Children-Food Interaction With an Interactive Cooking Toolkit. International Journal of Human–Computer Interaction41, 15 (2025), 9731–9751

work page 2025
[62]

Jane Wardle, Carol Ann Guthrie, Saskia Sanderson, and Lorna Rapoport. 2001. Development of the children’s eating behaviour questionnaire.The Journal of Child Psychology and Psychiatry and Allied Disciplines42, 7 (2001), 963–970

work page 2001
[63]

Hilde Weiser, Maria Waling, and Ingela Bohm. 2026. Food-related sensory activi- ties for children in educational settings: a scoping review.Appetite216 (2026), 108259

work page 2026
[64]

Hazel Wolstenholme, Colette Kelly, Marita Hennessy, and Caroline Heary. 2020. Childhood fussy/picky eating behaviours: A systematic review and synthesis of qualitative studies.International Journal of Behavioral Nutrition and Physical Activity17, 1 (2020), 2

work page 2020
[65]

The struggle is a part of the experience

Yuxing Wu, Andrew D Miller, Chia-Fang Chung, and Elizabeth Kaziunas. 2024. " The struggle is a part of the experience": Engaging Discontents in the Design of Family Meal Technologies.Proceedings of the ACM on Human-Computer Interaction8, CSCW2 (2024), 1–33

work page 2024
[66]

Wenjie Xu, Zhoutong Yu, Yikun Liu, and Fangtian Ying. 2025. Accompany Sleep: Using GenAI to Create Bedtime Stories for Mediating Parent-Child Relationships in LBC Families. InProceedings of the 2025 CHI Conference on Human Factors in Computing Systems. 1–19

work page 2025
[67]

unspecified

Chao Zhang, Cheng Yao, Jiayi Wu, Weijia Lin, Lijuan Liu, Ge Yan, and Fangtian Ying. 2022. StoryDrawer: a child–AI collaborative drawing system to support children’s creative visual storytelling. InProceedings of the 2022 CHI conference on human factors in computing systems. 1–15. StoryEcho Conference acronym ’XX, June 03–05, 2018, Woodstock, NY A Formativ...

work page 2022
[68]

Infer a suitable episode pattern from story_arc + recap_and_goal

work page
[69]

Always focus story theme on the concrete food instance

work page
[70]

picky food trying

Build the episode internally; output ONLY the final structured JSON. Story requirements: - Keep continuity (world/roles/rituals/recurring objects) and keep the food anchor central. - Tone must be low-pressure: no force, blame, threats, punishment, transactional reward framing, or medical/nutrition diagnosis. - Chinese must be natural spoken text for ages ...

work page 2018
[71]

If self_description clearly indicates the child tasted, ate, or made progress, choose Praise

work page
[72]

If self_description clearly indicates avoidance or difficulty, choose Encourage

work page
[73]

Otherwise, use the rating: if self_rating >= 7, choose Praise; if self_rating <= 6, choose Encourage

work page
[74]

Global style constraints (anti-repetition): - Avoid formulaic openings

If rating conflicts with description, follow the description; if uncertain, choose Encourage. Global style constraints (anti-repetition): - Avoid formulaic openings. The first sentence MUST NOT contain nickname OR picky_food. - Do NOT start with generic comforting, evaluative, or overused praise phrases, or close variants. - Avoid repeating the same verb ...

work page
[75]

First sentence contains neither nickname nor picky_food

work page
[76]

nickname appears exactly once; picky_food appears >= 1

work page
[77]

Includes the two required elements for the chosen type

work page
[78]

If any check fails, rewrite and re-check, then output

<= 50 characters and not highly similar to recent_phrases; no banned starter phrases. If any check fails, rewrite and re-check, then output. Conference acronym ’XX, June 03–05, 2018, Woodstock, NY Zhou et al. D Detailed System Workflows Figure 3: Overview of StoryEcho’s system-level design. The loop begins with avatar creation (a) and story generation (b)...

work page 2018