I Lead, You Help but Only with Enough Details: Understanding User Experience of Co-Creation with Artificial Intelligence
The DOI matches its Crossref record; 50 of the 51 references it cites were found in a registry or an index.
Abstract
Recent advances in artificial intelligence (AI) have increased the opportunities for users to interact with the technology. Now, users can even collaborate with AI in creative activities such as art. To understand the user experience in this new user--AI collaboration, we designed a prototype, DuetDraw, an AI interface that allows users and the AI agent to draw pictures collaboratively. We conducted a user study employing both quantitative and qualitative methods. Thirty participants performed a series of drawing tasks with the think-aloud method, followed by post-hoc surveys and interviews. Our findings are as follows: (1) Users were significantly more content with DuetDraw when the tool gave detailed instructions. (2) While users always wanted to lead the task, they also wanted the AI to explain its intentions but only when the users wanted it to do so. (3) Although users rated the AI relatively low in predictability, controllability, and comprehensibility, they enjoyed their interactions with it during the task. Based on these findings, we discuss implications for user interfaces where users can collaborate with AI in creative works.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
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?
In the citing paper
“Oh et al. noted that excessive explanation can harm the user experience [8].”
From Dynamic Selection of Reliance Calibration Cues With AI Reliance Model (2023) · cites this paper as [8]
Citations
Cites
LeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126
The Discovery of Grounded Theory: Strategies for Qualitative Research.
Wagner, H. R., Glaser, B. G., & Strauss, A. L. (1968) · Social Forces · doi:10.2307/2575405 · Cited by 46,361
The Discovery of Grounded Theory; Strategies for Qualitative Research
Glaser, B. G., Strauss, A. L., & Strutzel, E. (1968) · Nursing Research · doi:10.1097/00006199-196807000-00014 · Cited by 39,449
Human-level control through deep reinforcement learning
Mnih, V., Kavukcuoglu, K., Silver, D., Rusu, A. A., Veness, J., Bellemare, M. G., Graves, A., Riedmiller, M., Fidjeland, A. K., Ostrovski, G., et al. (2015) · Nature · doi:10.1038/nature14236 · Cited by 30,357
Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification
He, K., Zhang, X., Ren, S., & Sun, J. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.123 · Cited by 19,741 · cited 1×
“It is the age of artificial intelligence (AI), and recent advances in deep learning have yielded AI with capabilities comparable to those of humans in various fields [20, 30, 39].”
BackgroundDeep learning in neural networks: an overview
Schmidhuber, J. (2015) · Neural Networks · doi:10.1016/j.neunet.2014.09.003 · Cited by 18,570
Mastering the game of Go with deep neural networks and tree search
Silver, D., Huang, A., Maddison, C. J., Guez, A., Sifre, L., van den Driessche, G., Schrittwieser, J., Antonoglou, I., Panneershelvam, V., Lanctot, M., et al. (2016) · Nature · doi:10.1038/nature16961 · Cited by 15,612 · cited 1×
“It will not only assist humans in repetitive and arduous tasks but also take on complex and elaborative works [32, 38, 49].”
BackgroundThe Discovery of Grounded Theory
Glaser, B. G., & Strauss, A. L. (2017) · The Discovery of Grounded Theory · doi:10.4324/9780203793206-1 · Cited by 8,344 · cited 1×
“The qualitative data from the think-aloud sessions and inter-views were transcribed and analyzed using grounded theory techniques [14].”
Method(2013) · Cited by 3,740
End to End Learning for Self-Driving Cars
Bojarski, M., Del Testa, D., Dworakowski, D., Firner, B., Flepp, B., Goyal, P., Jackel, L. D., Monfort, M., Muller, U., Zhang, J., et al. (2016) · arXiv · doi:10.48550/arxiv.1604.07316 · Cited by 3,198
Generating Sequences With Recurrent Neural Networks
Graves, A. (2013) · arXiv · doi:10.48550/arxiv.1308.0850 · Cited by 2,894
Human-level concept learning through probabilistic program induction
Lake, B. M., Salakhutdinov, R., & Tenenbaum, J. B. (2015) · Science · doi:10.1126/science.aab3050 · Cited by 2,817 · cited 1×
“It is the age of artificial intelligence (AI), and recent advances in deep learning have yielded AI with capabilities comparable to those of humans in various fields [20, 30, 39].”
BackgroundA Neural Algorithm of Artistic Style
Gatys, L., Ecker, A., & Bethge, M. (2016) · Journal of Vision · doi:10.1167/16.12.326 · Cited by 2,612
Generating Sentences from a Continuous Space
Bowman, S. R., Vilnis, L., Vinyals, O., Dai, A., Jozefowicz, R., & Bengio, S. (2016) · Proceedings of The 20th SIGNLL Conference on Computational Natural Language Learning · doi:10.18653/v1/k16-1002 · Cited by 2,061 · cited 2×
“It is also being applied in creative areas considered unique to humans, such as writing [4, 51], musical composition [7, 22], and drawing [5].”
BackgroundDeepDriving: Learning Affordance for Direct Perception in Autonomous Driving
Chen, C., Seff, A., Kornhauser, A., & Xiao, J. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.312 · Cited by 1,876 · cited 1×
“AI is expected to become increasingly prevalent in numerous areas [3, 6, 16, 59].”
BackgroundGenerating Text with Recurrent Neural Networks
Sutskever, I., Martens, J., & Hinton, G. E. (2011) · International Conference on Machine Learning · Cited by 1,783
Greenspan, H., van Ginneken, B., & Summers, R. M. (2016) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2016.2553401 · Cited by 1,700 · cited 1×
“AI is expected to become increasingly prevalent in numerous areas [3, 6, 16, 59].”
BackgroundProceedings of the 29th International Conference on Machine Learning (ICML-12)
Langford, J. C., & Pineau, J. (2012) · arXiv (Cornell University) · doi:10.48550/arxiv.1207.4676 · Cited by 1,618
Principles of mixed-initiative user interfaces
Horvitz, E. (1999) · Proceedings of the SIGCHI conference on Human factors in computing systems the CHI is the limit - CHI '99 · doi:10.1145/302979.303030 · Cited by 1,490 · cited 1×
“Further studies have been conducted on how to take the initiative with an agent when arranging collaboration between users and computers [21, 53].”
BackgroundKittur, A., Nickerson, J. V., Bernstein, M., Gerber, E., Shaw, A., Zimmerman, J., Lease, M., & Horton, J. (2013) · Proceedings of the 2013 conference on Computer supported cooperative work · doi:10.1145/2441776.2441923 · Cited by 1,034 · cited 1×
“Moreover, while humans can guide AI, AI can also guide humans [26, 55].”
(2009) · neural information processing systems · Cited by 962
(1988) · Knowledge-Based Systems · doi:10.1016/0950-7051(88)90091-3 · Cited by 874
Explaining the user experience of recommender systems
Knijnenburg, B. P., Willemsen, M. C., Gantner, Z., Soncu, H., & Newell, C. (2012) · User Modeling and User-Adapted Interaction · doi:10.1007/s11257-011-9118-4 · Cited by 799 · cited 1×
“Many HCI researchers have conducted user studies on various AI interfaces [28, 42, 58], and the concept of algorithmic experience has been suggested as a new perspective from which to view the user experience of AI interfaces [41].”
BackgroundThe UX Book: Process and Guidelines for Ensuring a Quality User Experience
Hartson, R., & Pyla, P. S. (2012) · Cited by 659
Photography in Anthropology: A Report on Two Experiments
COLLIER, J. (1957) · American Anthropologist · doi:10.1525/aa.1957.59.5.02a00100 · Cited by 631 · cited 1×
“In this process, we used the photo projective technique [8], showing users the pictures they had just drawn so that they could easily recall their memories of the tasks.”
MethodA New Chatbot for Customer Service on Social Media
Xu, A., Liu, Z., Guo, Y., Sinha, V., & Akkiraju, R. (2017) · Proceedings of the 2017 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3025453.3025496 · Cited by 550 · cited 1×
“Many HCI researchers have conducted user studies on various AI interfaces [28, 42, 58], and the concept of algorithmic experience has been suggested as a new perspective from which to view the user experience of AI interfaces [41].”
BackgroundDirect manipulation vs. interface agents
Shneiderman, B., & Maes, P. (1997) · Interactions · doi:10.1145/267505.267514 · Cited by 518 · cited 3×
“In addition, we included three extra criteria that have been pointed out in the AI interface issue [18, 23, 48]: 13) predictability, 14) comprehensibility , and 15) controllability .”
BackgroundResultControlling Perceptual Factors in Neural Style Transfer
Gatys, L. A., Ecker, A. S., Bethge, M., Hertzmann, A., & Shechtman, E. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.397 · Cited by 486 · cited 1×
“also developed a neural network for blending the content of one image and the style of another image [13].”
Background"Alexa is my new BFF": Social Roles, User Satisfaction, and Personification of the Amazon Echo
Purington, A., Taft, J. G., Sannon, S., Bazarova, N. N., & Taylor, S. H. (2017) · Proceedings of the 2017 CHI Conference Extended Abstracts on Human Factors in Computing Systems · doi:10.1145/3027063.3053246 · Cited by 476
Exploring Models and Data for Image Question Answering
Ren, M., Kiros, R., & Zemel, R. S. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1505.02074 · Cited by 359 · cited 1×
“They can even work together to produce reasonable results in various creative tasks, including writing, drawing, and problem solving [4, 12, 43].”
BackgroundDeep learning of feature representation with multiple instance learning for medical image analysis
Xu, Y., Mo, T., Feng, Q., Zhong, P., Lai, M., & Chang, E. I.-C. (2014) · 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp.2014.6853873 · Cited by 354 · cited 1×
“AI is expected to become increasingly prevalent in numerous areas [3, 6, 16, 59].”
BackgroundTullis, T. S., & Albert, W. (2013) · Morgan Kaufmann Publishers Inc. eBooks · Cited by 332
Artificial Intelligence for Games
Millington, I., & Funge, J. (2018) · CRC Press eBooks · doi:10.1201/9781315375229 · Cited by 319 · cited 1×
“It will not only assist humans in repetitive and arduous tasks but also take on complex and elaborative works [32, 38, 49].”
Background(2008) · doi:10.1016/b978-0-12-373558-4.x0001-5 · Cited by 287
Creativity Support Tools: Report From a U.S. National Science Foundation Sponsored Workshop
Shneiderman, B., Fischer, G., Czerwinski, M., Resnick, M., Myers, B., Candy, L., Edmonds, E., Eisenberg, M., Giaccardi, E., Hewett, T., et al. (2006) · International Journal of Human-Computer Interaction · doi:10.1207/s15327590ijhc2002_1 · Cited by 274
Semantic Style Transfer and Turning Two-Bit Doodles into Fine Artworks
Champandard, A. J. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1603.01768 · Cited by 184 · cited 1×
“It is also being applied in creative areas considered unique to humans, such as writing [4, 51], musical composition [7, 22], and drawing [5].”
BackgroundAnthropomorphism, agency, and ethopoeia: computers as social actors
Nass, C., Steuer, J., Tauber, E., & Reeder, H. (1993) · INTERACT '93 and CHI '93 conference companion on Human factors in computing systems - CHI '93 · doi:10.1145/259964.260137 · Cited by 162 · cited 1×
“People personified it as a human based on its detailed features [40].”
BackgroundDavis, N., Hsiao, C.-P., Yashraj Singh, K., Li, L., & Magerko, B. (2016) · Proceedings of the 21st International Conference on Intelligent User Interfaces · doi:10.1145/2856767.2856795 · Cited by 138 · cited 1×
“developed Drawing Apprentice, which can collaborate with users by analyzing their drawn input and responding in real time in improvisational interactions [9, 10].”
BackgroundShifting viewpoints: Artificial intelligence and human–computer interaction
Winograd, T. A. (2006) · Artificial Intelligence · doi:10.1016/j.artint.2006.10.011 · Cited by 103 · cited 1×
“As users and AI are now interacting in these novel ways, understanding the user experience with these intelligent interfaces has become a critical issue in the human–computer interaction community [11, 25, 44, 56].”
BackgroundText-based LSTM networks for Automatic Music CompositionPreprint
Choi, K., Fazekas, G., & Sandler, M. B. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1604.05358 · Cited by 103 · cited 1×
“It is also being applied in creative areas considered unique to humans, such as writing [4, 51], musical composition [7, 22], and drawing [5].”
BackgroundOh, C., Lee, T., Kim, Y., Park, S., Kwon, S., & Suh, B. (2017) · Proceedings of the 2017 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3025453.3025539 · Cited by 84
Self-citationSoftware Agents and Soft Computing Towards Enhancing Machine Intelligence
(1997) · Lecture notes in computer science · doi:10.1007/3-540-62560-7 · Cited by 74
Rethinking the Relationship between Humans and Computers
Ren, X. (2016) · Computer · doi:10.1109/mc.2016.253 · Cited by 53 · cited 2×
“As users and AI are now interacting in these novel ways, understanding the user experience with these intelligent interfaces has become a critical issue in the human–computer interaction community [11, 25, 44, 56].”
BackgroundUnderstanding and Dealing With Usability Side Effects of Intelligent Processing
Jameson, A. (2009) · AI Magazine · doi:10.1609/aimag.v30i4.2274 · Cited by 47 · cited 3×
“In addition, we included three extra criteria that have been pointed out in the AI interface issue [18, 23, 48]: 13) predictability, 14) comprehensibility, and 15) controllability.”
BackgroundResultArtificial Intelligence for Games (The Morgan Kaufmann Series in Interactive 3D Technology)
Millington, I. (2006) · Cited by 46
Choice: abidcating or exercising?
Leong, T., Howard, S., & Vetere, F. (2008) · Proceedings of the SIGCHI Conference on Human Factors in Computing Systems · doi:10.1145/1357054.1357168 · Cited by 36 · cited 1×
“This could be a way of providing an interesting and pleasant user experience [33] during the task.”
BackgroundHuman Computer Integration versus Powerful Tools
Farooq, U., Grudin, J., Shneiderman, B., Maes, P., & Ren, X. (2017) · Proceedings of the 2017 CHI Conference Extended Abstracts on Human Factors in Computing Systems · doi:10.1145/3027063.3051137 · Cited by 36 · cited 2×
“As users and AI are now interacting in these novel ways, understanding the user experience with these intelligent interfaces has become a critical issue in the human–computer interaction community [11, 25, 44, 56].”
BackgroundChallenges in Developing User-Adaptive Intelligent User Interfaces
Hartmann, M. (2009) · LWA · Cited by 35
Artificial intelligence: think again
Kaplan, J. (2016) · Communications of the ACM · doi:10.1145/2950039 · Cited by 35 · cited 2×
“As users and AI are now interacting in these novel ways, understanding the user experience with these intelligent interfaces has become a critical issue in the human–computer interaction community [11, 25, 44, 56].”
BackgroundCo-Creative Drawing Agent with Object Recognition
Davis, N., Hsiao, C.-P., Singh, K. Y., & Magerko, B. (2016) · Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment · doi:10.1609/aiide.v12i1.12863 · Cited by 24 · cited 1×
“developed Drawing Apprentice, which can collaborate with users by analyzing their drawn input and responding in real time in improvisational interactions [9, 10].”
Background
Research works printed but not linked: 16
- Nick Babich. 2016. 5 Essential UX Rules for Dialog Design. (2016). Retrieved September 18, 2017 from http: //babich.biz/5-essential-ux-rules-for-dialog-design/.
- 10.5555/3505288.3505290 · doi:10.5555/3505288.3505290
- David Ha and Douglas Eck. 2017. A Neural Representation of Sketch Drawings. arXiv preprint arXiv:1704.03477 (2017). · arXiv
- 10.5555/2207824 · doi:10.5555/2207824
- Allen Huang and Raymond Wu. 2016. Deep learning for music. arXiv preprint arXiv:1606.04930 (2016). · arXiv
- Jonas Jongejan, Henry Rowley, Takashi Kawashima, Jongmin Kim, and Nick Fox-Gieg. 2017. Quick, Draw! (2017). Retrieved September 18, 2017 from https://quickdraw.withgoogle.com.
- Google Creative Lab. 2017. AutoDraw. (2017). Retrieved September 18, 2017 from https://experiments.withgoogle.com/chrome/autodraw.
- Clayton Lewis and John Rieman. 1993. Task-centered user interface design. A Practical Introduction (1993).
- Arnold M Lund. 2001. Measuring Usability with the USE Questionnaire12. Usability interface 8, 2 (2001), 3--6.
- Yotam Mann. 2017. AI Duet. (2017). Retrieved September 18, 2017 from https://experiments.withgoogle.com/ai/ai-duet.
- 10.5555/1199865 · doi:10.5555/1199865
- 10.5555/2031622 · doi:10.5555/2031622
- Luke Swartz. 2003. Why people hate the paperclip: Labels appearance behavior and social responses to user interface agents. Ph.D. Dissertation. Stanford University Palo Alto CA.
- 10.1609/aimag.v28i2.2035 · doi:10.1609/aimag.v28i2.2035
- 10.5555/646107.678974 · doi:10.5555/646107.678974
- Optimal Workshop. 2016. Reframer. (2016). Retrieved September 21, 2016 from https://www.optimalworkshop.com/reframer.
Cited by
Wu, T., Terry, M., & Cai, C. J. (2022) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3491102.3517582 · Cited by 483
Rezwana, J., & Maher, M. L. (2023) · ACM Transactions on Computer-Human Interaction · doi:10.1145/3519026 · Cited by 342
Haque, A. B., Islam, A. K. M. N., & Mikalef, P. (2023) · Technological Forecasting and Social Change · doi:10.1016/j.techfore.2022.122120 · Cited by 240
Novice-AI Music Co-Creation via AI-Steering Tools for Deep Generative Models
Louie, R., Coenen, A., Huang, C. Z., Terry, M., & Cai, C. J. (2020) · Proceedings of the 2020 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3313831.3376739 · Cited by 271
Stige, Å., Zamani, E. D., Mikalef, P., & Zhu, Y. (2024) · Information Technology & People · doi:10.1108/itp-07-2022-0519 · Cited by 167
Metadata
- Authors
- Oh, C., Song, J., Choi, J., Kim, S., Lee, S., & Suh, B.
- Affiliations
- Seoul National University (KR)
- Venue
- Proceedings of the 2018 CHI Conference on Human Factors in Computing Systems
- Publisher
- ACM
- Published
- 2018-04-21
- Pages
- 1-13
- OpenAlex
- W2796000004
- Cited by
- 301
- References
- 51
- Citations by year
- 2026: 46 · 2025: 60 · 2024: 62 · 2023: 38 · 2022: 35 · 2021: 27 · 2020: 21 · 2019: 10 · 2018: 2
- FWCI
- 12.09
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- CHI Conference on Human Factors in Computing Systems (publishedVersion)
- Funders
- Institute for Information communications Technology Promotio (No.2017-0-00693)
- Topics
- Physical Sciences › Computer Science › Human-Computer Interaction › Innovative Human-Technology Interaction
- Physical Sciences › Computer Science › Human-Computer Interaction › Usability and User Interface Design
- Physical Sciences › Computer Science › Human-Computer Interaction › Interactive and Immersive Displays
- Keywords
- human-AI collaboration, user experience, AI interface design, task-oriented leadership, explainable AI, predictability, controllability, comprehensibility, creative work, user-AI interaction
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
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.