Comparative Study of Generative AI and Traditional Tools for Evaluating Creativity and Efficiency in UI/UX Desig
Open accessThe DOI matches its Crossref record; 19 of the 19 references it cites were found in a registry or an index.
Abstract
In the modern software industry, the creation of user interface (UI) and user experience (UX) design is an essential activity that is increasingly adopting generative artificial intelligence (AI) tools. With this growing trend, it is crucial to examine the novelty and creativity of AI-generated design outputs in comparison to those produced by traditional workflows without any AI support. The goal of this study is to quantitatively compare the cognitive load, creativity, and task completion time of UI/UX design outputs created using the traditional design tool named Figma and the generative AI tool named Galileo AI. The NASA task load index (NASA-TLX), creative product semantic scale (CPSS), and number of minutes taken to complete a design task are used to quantify cognitive load, creativity, and task completion time, respectively. To compare these three metrics between AI and traditional groups, an experiment is conducted with novice and expert designers, separately. The results reveal that the generative AI tool significantly reduces both the cognitive load of designers and the time required to create UI/UX designs. For instance, independent samples t-tests show that the generative AI tool results in lower cognitive load scores than the traditional tool for both novices (2.22 ± 0.53 vs. 3.25 ± 0.70) and experts (2.42 ± 0.64 vs. 3.79 ± 0.52). Similarly, independent samples t-tests results indicate that the AI tool reduces average task completion time for both novices (24.38 vs. 42.69) and experts (23.78 vs. 48.44) compared to the traditional tool. On the other hand, the traditional tool consistently outperforms the generative AI tool in terms of creativity and innovation. For instance, independent samples t-tests results show that the traditional design tool yields higher creativity scores than the generative AI tool for both novices (3.94 ± 0.66 vs. 3.27 ± 0.74) and experts (4.17 ± 0.39 vs. 3.37 ± 0.44). Overall, the AI tool excels at enhancing efficiency; however, it still faces challenges in replicating the depth of human creativity and emotional understanding that are essential for creating engaging UI/UX designs.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The text we found for this paper looks like another document, so the self-check wasn’t run.
Citations
Cites
Development of NASA-TLX (Task Load Index): Results of Empirical and Theoretical Research
(1988) · Advances in Psychology · doi:10.1016/s0166-4115(08)62386-9 · Cited by 15,003
Cognitive Load During Problem Solving: Effects on Learning
Sweller, J. (1988) · Cognitive Science · doi:10.1016/0364-0213(88)90023-7 · Cited by 11,048
Likert scales, levels of measurement, and the “laws” of statistics
Norman, G. (2010) · Advances in Health Sciences Education · doi:10.1007/s10459-010-9222-y · Cited by 4,850
The standard definition of creativity
Runco, M. A., & Jaeger, G. J. (2012) · Creativity Research Journal · doi:10.1080/10400419.2012.650092 · Cited by 3,895
Analyzing and Interpreting Data From Likert-Type Scales
Sullivan, G. M., & Artino, A. R. (2013) · Journal of Graduate Medical Education · doi:10.4300/jgme-5-4-18 · Cited by 3,044
Resolving the 50‐year debate around using and misusing Likert scales
Carifio, J., & Perla, R. (2008) · Medical Education · doi:10.1111/j.1365-2923.2008.03172.x · Cited by 1,043
Analysis of Creative Products: Review and Synthesis*
BESEMER, S. P., & TREFFINGER, D. J. (1981) · The Journal of Creative Behavior · doi:10.1002/j.2162-6057.1981.tb00287.x · Cited by 358
The Effects of Generative AI on Design Fixation and Divergent Thinking
Wadinambiarachchi, S., Kelly, R. M., Pareek, S., Zhou, Q., & Velloso, E. (2024) · Proceedings of the CHI Conference on Human Factors in Computing Systems · doi:10.1145/3613904.3642919 · Cited by 320
User Experience Design Professionals’ Perceptions of Generative Artificial Intelligence
Li, J., Cao, H., Lin, L., Hou, Y., Zhu, R., & El Ali, A. (2024) · Proceedings of the CHI Conference on Human Factors in Computing Systems · doi:10.1145/3613904.3642114 · Cited by 163
AI as a co-creator and a design material: Transforming the design process
Yu, W. F. (2025) · Design Studies · doi:10.1016/j.destud.2025.101303 · Cited by 141
Research works printed but not linked: 4
- [1] H. R. Hartson and P. S. Pyla, The UX Book: Agile UX Design for a Quality User Experience, 2nd ed. Cambridge, MA, USA: Morgan Kaufmann, 2019.
- [17] M. A. Shahab, “The Impact of Generative AI on UI Design for Mobile Applications in Terms of Efficiency Using SPACE Framework: A Survey-Based Study from Mobile Application Designers/Developers,” M.S. thesis, Faculty of Information Technology and Communication Sciences, Tampere Univ., Tampere, Finland, Nov. 2024.
- [18] “Concerns and Challenges of AI Tools in the UI/UX Design Process: A Cross-Sectional Survey.” Accessed: May 19, 2026. [Online]. Available: https://www.researchgate.net/publication/380522812_Concerns_and_Challenges_of_AI_Tools_in_the_UIUX_Design_Process_A_Cross-Sectional_Survey
- This version is in CrossRef/IEEE reference style, with no blank lines between references and corrected
Metadata
- Authors
- Daud, M., Shahzad, I., & Mughal, W.
- Affiliations
- National University of Modern Languages (PK)
- ORCID
- Daud, Marriam
- Venue
- International Journal of Innovations in Science and Technology
- Publisher
- 50Sea
- Published
- 2026-05-11
- Pages
- 924
- ISSN
- 2618-1630 (ISSN-L)
- 2709-6130
- OpenAlex
- W7167723788
- Cited by
- 0
- References
- 18
- FWCI
- 0.00
- Type
- journal article
- Language
- en
- Open access
- diamond
- doi.org
- Locations
- International Journal of Innovations in Science and Technology (publishedVersion, cc-by)
- Topics
- Physical Sciences › Computer Science › Human-Computer Interaction › Usability and User Interface Design
- Physical Sciences › Computer Science › Computer Graphics and Computer-Aided Design › Digital Media and Visual Art
- Physical Sciences › Engineering › Mechanical Engineering › Design Education and Practice
- Keywords
- generative AI, UI/UX design, design creativity, cognitive load, task completion time, Figma, NASA-TLX, AI-assisted design
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.
A second model labelled each claim on 2026-11-11 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Comparative Study of Generative AI and Traditional Tools for Evaluating Creativity and Efficiency in UI/UX Desig. https://app.cochat.ai/papers/10.33411/ijist/1876
- The paper
- Daud, M., Shahzad, I., & Mughal, W. (2026). Comparative Study of Generative AI and Traditional Tools for Evaluating Creativity and Efficiency in UI/UX Desig. International Journal of Innovations in Science and Technology. https://doi.org/10.33411/ijist/1876
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.