Human Interpretation, AI Support: A Workflow for Thematic Analysis using Large Language Models in Co-design
DOI:
https://doi.org/10.23726/cij.2026.1827Keywords:
co-design, thematic analysis, LLM, qualitative analysisAbstract
This methodological note describes a workflow for thematic analysis in which Large Language Models (LLMs) are used to support specific analytic tasks on Co-creation and Co-design user data. LLMs are advanced artificial intelligence systems trained on large volumes of textual data that can generate articulated textual responses when prompted. The primary benefit of this workflow is the streamlining of time-intensive analytic tasks, enabling Co-creation and Co-design teams to maintain methodological rigour in qualitative analysis while working under tight time constraints.
References
Barany, A. et al. (2024). ChatGPT for Education Research: Exploring the Potential of Large Language Models for Qualitative Codebook Development. In: Olney, A.M., Chounta, IA., Liu, Z., Santos, O.C., Bittencourt, I.I. (eds) Artificial Intelligence in Education. AIED 2024. Lecture Notes in Computer Science, vol 14830. Springer, Cham. https://doi.org/10.1007/978-3-031-64299-9_10
Braun, V., & Clarke, V. (2006). Using thematic analysis in psychology. Qualitative Research in Psychology, 3(2): 77–101. https://doi.org/10.1191/1478088706qp063oa
Braun, V., & Clarke, V. (2021). Can I use TA? Should I use TA? Comparing reflexive thematic analysis and other pattern-based analytic approaches. Counselling and Psychotherapy Research, 21(1): 37–47. https://doi.org/10.1002/capr.12360
De Paoli, S. (2023). Performing an Inductive Thematic Analysis of Semi-Structured Interviews With a Large Language Model: An Exploration and Provocation on the Limits of the Approach. Social Science Computer Review, 42(4): 997-1019. https://doi.org/10.1177/08944393231220483
De Paoli, S. (2025). Why I Reject the Use of Generative Artificial Intelligence in Qualitative Analysis. Available at SSRN: https://ssrn.com/abstract=5722002 or http://dx.doi.org/10.2139/ssrn.5722002
De Paoli, S., & Fawzi, A. (2025). TALLMesh: a simple application for performing thematic analysis with large language models. arXiv:2504.13892. https://doi.org/10.48550/arXiv.2504.13892
Morrow, D., Pehar, F., Silver, C. A., Fletcher, K. A., & De Paoli, S. (2025). Towards Human-AI collaborative methods in UX: a qualitative case study for discovery research platforms. In 38th International BCS Human-Computer Interaction Conference (pp. 519-529). BCS Learning & Development. https://doi.org/10.14236/ewic/BCSHCI2025.58
Pacherie, E. (2012). The Phenomenology of Joint Action: Self-Agency versus Joint Agency. In: Joint Attention, 343–390. The MIT Press. https://doi.org/10.7551/mitpress/8841.003.0017
Pearce, T., Maple, M., Shakeshaft, A., Wayland, S., & McKay, K. (2020). What is the co-creation of new knowledge? A content analysis and proposed definition for health interventions. International Journal of Environmental Research and Public Health, 17(7), 2229. https://doi.org/10.3390/ijerph17072229
Yan, L., Echeverria, V., Fernandez-Nieto, G. M., Jin, Y., Swiecki, Z., Zhao, L., Gašević, D., & Martinez-Maldonado, R. (2024). Human-AI Collaboration in Thematic Analysis using ChatGPT: A User Study and Design Recommendations. Extended Abstracts of the CHI Conference on Human Factors in Computing Systems, 1–7. https://doi.org/10.1145/3613905.3650732
Downloads
Published
How to Cite
Issue
Section
Categories
License
Copyright (c) 2026 Crystal Silver, Diane Morrow, Stefano De Paoli
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
