Can Children Emulate a Robotic Non-Player Character's Figural Creativity?
Open accessAbstract
Can intelligent non-player game characters (NPCs) increase children's creativity during collaborative gameplay? Children's creativity is influenced by collaborative play with creative peers through social emulation. In this paper, we study children's emulation of an AI-enabled social Non-Player Character (NPC) as a new type of game mechanism to elicit creative expression. We developed Magic Draw, a collaborative drawing game designed to foster children's figural creativity that allows us to investigate the efficacy of an NPC's creativity demonstration in enhancing children's creativity in the resulting drawings. The NPC is an emotively expressive social robot that plays Magic Draw with a child as a peer-like playmate. We present the results of a study in which participants co-draw figures with a social robot that demonstrates different levels of figural creativity, to understand whether an NPC's creativity in its own contributions stimulates figural creativity in children. 78 participants (ages 5--10) were randomly assigned to a non-creative robot control condition (C-) and a creative robot condition (C+). Participants who interacted with the creative robot generated significantly more creative drawings, and hence exhibited higher levels of figural creativity. We infer that the social robotic peers' demonstration of figural creativity in a collaborative drawing game is emulated by young children. We discuss a new game design principle grounded in the social learning mechanism of emulation, specifically, that social and intelligent NPCs in games should demonstrate creative behavior to foster the same in human players.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Several reviewed studies involved multiple AI roles.
“with several studies [4,11,59,62,63] involving multiple roles”
From Child-AI Co-Creation: A Review of the Current Research Landscape and a Proposal for Six Design Considerations (2025) · cites this paper as [4]
Some reviewed systems position AI as a facilitator, offering hints, prompts, or feedback to guide students' thinking rather than generating full responses.
“Rather than enabling AI to generate full responses, some systems position AI as a facilitator [4,10,11,29,30,35,59,61,63], offering hints, prompts, or feedback to guide students' thinking.”
From Child-AI Co-Creation: A Review of the Current Research Landscape and a Proposal for Six Design Considerations (2025) · cites this paper as [4]
Several reviewed studies report that AI systems, due to model limitations or interaction structure, can narrow children's ideation or subtly shape the direction of their creative output.
“Several studies report that AI systems, due to inherent model limitations or the way interactions are structured, can narrow children's ideation or subtly shape the direction of their creative output [4,11,37,62,63].”
From Child-AI Co-Creation: A Review of the Current Research Landscape and a Proposal for Six Design Considerations (2025) · cites this paper as [4]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
The citation lists haven’t been fetched yet
References 56 · Cited by 20
Research works printed but not linked: 4
- G Fischer. 1993. Embedding computer-based critics in the contexts of design, human factors in computing systems. In INTERCHI'93 Conference Proceedings, Amsterdam, the Netherlands. ACM Press.
- Florian Geyer, Jochen Budzinski, and Harald Reiterer. 2012. IdeaVis: a hybrid workspace and interactive visualization for paper-based collaborative sketch- ing sessions. In Proceedings of the 7th Nordic Conference on Human-Computer Interaction: Making Sense Through Design. 331-340.
- Peter H Kahn Jr, Takayuki Kanda, Hiroshi Ishiguro, Brian T Gill, Solace Shen, Jolina H Ruckert, and Heather E Gary. 2016. Human creativity can be facilitated through interacting with a social robot. In The Eleventh ACM/IEEE International Conference on Human Robot Interaction. IEEE Press, 173-180.
- Randi Williams. 2018. Leveraging social robots to aid preschool children's artificial intelligence education. Ph.D. Dissertation. Master's thesis. MIT. https://www. media. mit. edu/publications/pop-study-2018.
- Authors
- Ali, S., Park, H. W., & Breazeal, C.
- Affiliations
- Massachusetts Institute of Technology (US)
- Venue
- Proceedings of the Annual Symposium on Computer-Human Interaction in Play
- Publisher
- ACM
- Published
- 2020-11-02
- Pages
- 499-509
- OpenAlex
- W3097551320
- Cited by
- 20
- References
- 56
- Citations by year
- 2026: 4 · 2025: 4 · 2024: 5 · 2022: 1 · 2021: 5 · 2020: 1
- FWCI
- 2.47
- Type
- conference paper
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- Locations
- Annual Symposium on Computer-Human Interaction in Play (publishedVersion, cc-by)
- DSpace@MIT (Massachusetts Institute of Technology) (submittedVersion, cc-by-nc)
- Topics
- Social Sciences › Psychology › Social Psychology › Social Robot Interaction and HRI
- Social Sciences › Psychology › Experimental and Cognitive Psychology › Creativity in Education and Neuroscience
- Social Sciences › Psychology › Developmental and Educational Psychology › Educational Games and Gamification
- Keywords
- children's creativity, figural creativity, non-player characters, social robots, collaborative drawing, emulation, social learning, game design, collaborative gameplay
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review