CoChat

Mixed-Initiative Creative Interfaces

Open access
Deterding, Sebastian, Hook, Jonathan, Fiebrink, Rebecca, Gillies, Marco, Gow, Jeremy, Akten, Memo, Smith, Gillian, Liapis, Antonios, Compton, Kate · 2017 · Proceedings of the 2017 CHI Conference Extended Abstracts on Human Factors in Computing Systems

The DOI matches its Crossref record; 24 of the 24 references it cites were found in a registry or an index; 4 of the 48 sources its claims cite were checked for support.

Abstract

Enabled by artificial intelligence techniques, we are witnessing the rise of a new paradigm of computational creativity support: mixed-initiative creative interfaces put human and computer in a tight interactive loop where each suggests, produces, evaluates, modifies, and selects creative outputs in response to the other. This paradigm could broaden and amplify creative capacity for all, but has so far remained mostly confined to artificial intelligence for game content generation, and faces many unsolved interaction design challenges. This workshop therefore convenes CHI and game researchers to advance mixed-initiative approaches to creativity support.

Overview

CoChat Summary

TL;DR

This CHI'17 extended abstract proposes a workshop convening CHI and game-AI researchers to advance mixed-initiative creative interfaces (MICIs), in which human and computer take turns suggesting, producing, evaluating, modifying, and selecting creative outputs. It argues that MICI work is currently concentrated in procedural content generation for games and faces unsolved interaction-design challenges that HCI expertise could address.

Key findings

This is a workshop proposal, not an empirical study, so it reports no data-driven results. Its substantive claims are:

  • Creative interfaces cluster at two ends of a spectrum: traditional creativity support tools (human as creator, computer as tool) and computational creativity (computer as "heroic" AI creator, human as audience); MICIs occupy a third, middle position where both act as collaborators in a tight feedback loop.
  • MICI is realized chiefly in procedural content generation for games, using techniques such as evolutionary computation, heuristic search, or machine learning to (semi-)automatically create and evaluate art assets, game levels, or entire games.
  • Claimed advantages of existing MICI systems: vastly accelerated iterative exploration of solution spaces (enabling otherwise prohibitively time-consuming divergent exploration), accelerated learning about creative practice through probing and hypothesis-testing, rich lateral stimuli, and accessibility/enjoyment for non-professional and disabled user groups with benefits to wellbeing and societal inclusion.
  • MICIs outside games cited as relevant to HCI include urban design, sketching, interface design, prototyping musical instruments, and data visualization.

Methods

Not stated in the paper (no empirical design, data, or analysis). The document describes workshop organization: juried review of 2–6 page position papers, a target of 15–25 participants, thematic panels of 3–4 presentations alternating with poster/demo islands, small-group work facilitated by one HCI and one game-AI lead each, and post-workshop publication of accepted papers as CEUR workshop proceedings plus a write-up for ACM Interactions or Communications of the ACM.

Limitations

The paper states that MICI work has so far remained largely confined to game content generation and disconnected from creative interface researchers in HCI, and that MICIs in games have chiefly been designed by AI researchers for computationally literate user groups. It lists unsolved interface and interaction design challenges: enabling creators with little computational literacy to express ideas, constraints, or criteria in a computable manner; avoiding user fatigue and making interaction engaging; rendering computer design decisions legible and transparent; and identifying visualization patterns for computational design evaluations and modification/selection suggestions. Evident from the text: as a workshop proposal it presents no evidence, evaluation, or results, and its claims about MICI benefits are asserted with citations rather than demonstrated.

Model-written summary. Check it against the paper before relying on it.

Integrity signals

Registry

Crossref · 10.1145/3027063.3027072

Cites

24 of 24 references verified0 citation errors · 0 not checkable

Statistics

Nothing to recompute.

Verification

Claims the paper makes

2 Valid · 2 Not valid · 10 Not checked · 1 Own results and interpretations

5 more claims

Create a free account to see all 15 claims and to verify the 1 reference still open.

See all claims — free account
  • Probably not a substantial claim. 5

Create a free account to see these claims.

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?

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

Each contradiction between two passages listed here was confirmed by an independent check.

1 of 1

Citations

Cites

Research works printed but not linked: 3

  1. Jon McCormack and Mark D'Inverno . 2014 . On the Future of Computers and Creativity. AISB14 Symposium on Computational Creativity, 1--4. Jon McCormack and Mark D'Inverno. 2014. On the Future of Computers and Creativity. AISB14 Symposium on Computational Creativity, 1--4.
  2. Antonios Liapis , Georgios N Yannakakis , Constantine Alexopoulos , and Phil Lopes . 2016 . Can Computers Foster Human User's Creativity? Theory and Practice of Mixed-Initiative CoCreativity . Digital Culture & Education 8 , 2: 136 -- 153 . Antonios Liapis, Georgios N Yannakakis, Constantine Alexopoulos, and Phil Lopes. 2016. Can Computers Foster Human User's Creativity? Theory and Practice of Mixed-Initiative CoCreativity. Digital Culture & Education 8, 2: 136-- 153.
  3. Kate Compton and Michael Mateas . 2015 . Casual Creators. Proceedings of the Sixth International Conference on Computational Creativity, 228--235 . Kate Compton and Michael Mateas. 2015. Casual Creators. Proceedings of the Sixth International Conference on Computational Creativity, 228--235.

Cited by

See all 117

Metadata

Authors
Deterding, S., Hook, J., Fiebrink, R., Gillies, M., Gow, J., Akten, M., Smith, G., Liapis, A., & Compton, K.
Affiliations
  • University of York (GB)
  • Goldsmiths University of London (GB)
  • University of London (GB)
  • Northeastern University (US)
  • University of Malta (MT)
  • University of California, Santa Cruz (US)
Venue
Proceedings of the 2017 CHI Conference Extended Abstracts on Human Factors in Computing Systems
Publisher
ACM
Published
2017-05-06
Pages
628-635
OpenAlex
W2602896535
Cited by
117
References
22
Citations by year
2026: 18 · 2025: 23 · 2024: 23 · 2023: 18 · 2022: 12 · 2021: 8 · 2020: 10 · 2019: 3 · 2018: 2
FWCI
1.87
Type
conference paper
Language
en
Open access
Locations
  • CHI Conference Extended Abstracts on Human Factors in Computing Systems (CHI EA) (publishedVersion)
  • White Rose Research Online (University of Leeds, The University of Sheffield, University of York) (submittedVersion)
Funders
EPSRC/AHRC/Innovate UK (EP/M023265/1)
Topics
  • Physical Sciences › Computer Science › Artificial Intelligence › Artificial Intelligence in Games
  • Physical Sciences › Computer Science › Computer Graphics and Computer-Aided Design › Digital Media and Visual Art
  • Physical Sciences › Computer Science › Human-Computer Interaction › Innovative Human-Technology Interaction
Keywords
computational creativity, creativity support, human-computer interaction, game content generation, interaction design, human-computer collaboration

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.

The claim verdicts this report counts are experimental: their accuracy is not yet measured.

A language model drew the claims from the paper on 2026-09-30, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).

A second model labelled each claim on 2026-09-30 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).

Cited sources are checked with a language model’s help (gpt-6-sol).

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

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.