Towards human-AI collaborative methods in UX: a qualitative case study for discovery research platforms

Diane Morrow; Franjo Pehar; Crystal Silver; Kathy-Ann Fletcher; Stefano De Paoli

doi:10.14236/ewic/BCSHCI2025.58

Towards human-AI collaborative methods in UX: a qualitative case study for discovery research platforms

Diane Morrow, Franjo Pehar, Crystal Silver, Kathy-Ann Fletcher, Stefano De Paoli

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

1 Downloads (Pure)

Abstract

This paper introduces human and Artificial Intelligence (AI) collaboration for the preparation and analysis of empirical qualitative data. Through a case study, we explore this collaboration with user experiences of researchers across four research disciplines: (1) Molecular Dynamics; (2) Earth Systems; (3) Social Sciences and Humanities; and (4) Mathematics, alongside commercial data providers. Generative AI and Large Language Models (LLMs) conducted processes within the thematic analysis of empirical interview transcripts led by researchers. Over a six-month period, we iteratively translated user insights into design artefacts – user personas, scenarios, and tool functionalities. Here, we report on the focus of the analysis stages combining AI-process and critical human decision-making. This case study demonstrates how using generative AI can streamline traditional qualitative methods in discovery tool design, whilst maintaining quality of research outcomes. We highlight the stages required for delivery of meaningful, collaborative, user-centred design artefacts, and reflect on our Human-AI interactions.

Original language	English
Title of host publication	BCS HCI '25: Proceedings of the 38th International BCS Human-Computer Interaction Conference
Place of Publication	Swindon
Publisher	BCS Learning & Development Ltd.
Pages	519-529
Number of pages	11
DOIs	https://doi.org/10.14236/ewic/BCSHCI2025.58
Publication status	Published - 1 Nov 2025
Event	38th International BCS Human-Computer Interaction Conference: HCI4AI – Human Centred Approaches and their Impact on AI system design, application, and evaluation - Cardiff University, Cardiff, United Kingdom Duration: 9 Nov 2025 → 11 Nov 2025 Conference number: 38th https://www.britchi2025.co.uk/

Publication series

Name	Electronic Workshops in Computing (eWiC)
Publisher	BCS Learning & Development Ltd.
ISSN (Print)	1477-9358

Conference

Conference	38th International BCS Human-Computer Interaction Conference
Abbreviated title	BCS HCI 2025
Country/Territory	United Kingdom
City	Cardiff
Period	9/11/25 → 11/11/25
Internet address	https://www.britchi2025.co.uk/

Keywords

Human-AI interaction;
Qualitative research methods
Research discovery

Access to Document

10.14236/ewic/BCSHCI2025.58Licence: CC BY

DePaoli_TowardsHuman-AICollaborativeMethods_Published_2025Final published version, 1.21 MBLicence: CC BY

https://www.scienceopen.com/hosted-document?doi=10.14236/ewic/BCSHCI2025.58Licence: CC BY

Cite this

Morrow, D., Pehar, F., Silver, C., Fletcher, K.-A., & De Paoli, S. (2025). Towards human-AI collaborative methods in UX: a qualitative case study for discovery research platforms. In BCS HCI '25: Proceedings of the 38th International BCS Human-Computer Interaction Conference (pp. 519-529). (Electronic Workshops in Computing (eWiC)). BCS Learning & Development Ltd.. https://doi.org/10.14236/ewic/BCSHCI2025.58

@inproceedings{5a2b8cff60f64103a6a19180737465d6,

title = "Towards human-AI collaborative methods in UX: a qualitative case study for discovery research platforms",

abstract = "This paper introduces human and Artificial Intelligence (AI) collaboration for the preparation and analysis of empirical qualitative data. Through a case study, we explore this collaboration with user experiences of researchers across four research disciplines: (1) Molecular Dynamics; (2) Earth Systems; (3) Social Sciences and Humanities; and (4) Mathematics, alongside commercial data providers. Generative AI and Large Language Models (LLMs) conducted processes within the thematic analysis of empirical interview transcripts led by researchers. Over a six-month period, we iteratively translated user insights into design artefacts – user personas, scenarios, and tool functionalities. Here, we report on the focus of the analysis stages combining AI-process and critical human decision-making. This case study demonstrates how using generative AI can streamline traditional qualitative methods in discovery tool design, whilst maintaining quality of research outcomes. We highlight the stages required for delivery of meaningful, collaborative, user-centred design artefacts, and reflect on our Human-AI interactions.",

author = "Diane Morrow and Franjo Pehar and Crystal Silver and Kathy-Ann Fletcher and \{De Paoli\}, Stefano",

note = "{\textcopyright} Morrow et al. Published by BCS Learning and Development Ltd. Proceedings of BCS HCI 2025, UK This work is licensed under a Creative Commons Attribution 4.0 Unported License. To view a copy of this license, visit http://creativecommons.org/licenses/by/4.0/ Data availability statement: Not present.; 38th International BCS Human-Computer Interaction Conference : HCI4AI – Human Centred Approaches and their Impact on AI system design, application, and evaluation, BCS HCI 2025 ; Conference date: 09-11-2025 Through 11-11-2025",

year = "2025",

month = nov,

day = "1",

doi = "10.14236/ewic/BCSHCI2025.58",

language = "English",

series = "Electronic Workshops in Computing (eWiC)",

publisher = "BCS Learning \& Development Ltd.",

pages = "519--529",

booktitle = "BCS HCI '25: Proceedings of the 38th International BCS Human-Computer Interaction Conference",

url = "https://www.britchi2025.co.uk/",

}

Morrow, D, Pehar, F, Silver, C , Fletcher, K-A & De Paoli, S 2025, Towards human-AI collaborative methods in UX: a qualitative case study for discovery research platforms. in BCS HCI '25: Proceedings of the 38th International BCS Human-Computer Interaction Conference. Electronic Workshops in Computing (eWiC), BCS Learning & Development Ltd., Swindon, pp. 519-529, 38th International BCS Human-Computer Interaction Conference, Cardiff, United Kingdom, 9/11/25. https://doi.org/10.14236/ewic/BCSHCI2025.58

Towards human-AI collaborative methods in UX: a qualitative case study for discovery research platforms. / Morrow, Diane; Pehar, Franjo; Silver, Crystal et al.
BCS HCI '25: Proceedings of the 38th International BCS Human-Computer Interaction Conference. Swindon: BCS Learning & Development Ltd., 2025. p. 519-529 (Electronic Workshops in Computing (eWiC)).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Towards human-AI collaborative methods in UX

T2 - 38th International BCS Human-Computer Interaction Conference

AU - Morrow, Diane

AU - Pehar, Franjo

AU - Silver, Crystal

AU - Fletcher, Kathy-Ann

AU - De Paoli, Stefano

N1 - Conference code: 38th

PY - 2025/11/1

Y1 - 2025/11/1

N2 - This paper introduces human and Artificial Intelligence (AI) collaboration for the preparation and analysis of empirical qualitative data. Through a case study, we explore this collaboration with user experiences of researchers across four research disciplines: (1) Molecular Dynamics; (2) Earth Systems; (3) Social Sciences and Humanities; and (4) Mathematics, alongside commercial data providers. Generative AI and Large Language Models (LLMs) conducted processes within the thematic analysis of empirical interview transcripts led by researchers. Over a six-month period, we iteratively translated user insights into design artefacts – user personas, scenarios, and tool functionalities. Here, we report on the focus of the analysis stages combining AI-process and critical human decision-making. This case study demonstrates how using generative AI can streamline traditional qualitative methods in discovery tool design, whilst maintaining quality of research outcomes. We highlight the stages required for delivery of meaningful, collaborative, user-centred design artefacts, and reflect on our Human-AI interactions.

AB - This paper introduces human and Artificial Intelligence (AI) collaboration for the preparation and analysis of empirical qualitative data. Through a case study, we explore this collaboration with user experiences of researchers across four research disciplines: (1) Molecular Dynamics; (2) Earth Systems; (3) Social Sciences and Humanities; and (4) Mathematics, alongside commercial data providers. Generative AI and Large Language Models (LLMs) conducted processes within the thematic analysis of empirical interview transcripts led by researchers. Over a six-month period, we iteratively translated user insights into design artefacts – user personas, scenarios, and tool functionalities. Here, we report on the focus of the analysis stages combining AI-process and critical human decision-making. This case study demonstrates how using generative AI can streamline traditional qualitative methods in discovery tool design, whilst maintaining quality of research outcomes. We highlight the stages required for delivery of meaningful, collaborative, user-centred design artefacts, and reflect on our Human-AI interactions.

U2 - 10.14236/ewic/BCSHCI2025.58

DO - 10.14236/ewic/BCSHCI2025.58

M3 - Conference contribution

T3 - Electronic Workshops in Computing (eWiC)

SP - 519

EP - 529

BT - BCS HCI '25: Proceedings of the 38th International BCS Human-Computer Interaction Conference

PB - BCS Learning & Development Ltd.

CY - Swindon

Y2 - 9 November 2025 through 11 November 2025

ER -

Morrow D, Pehar F, Silver C , Fletcher KA , De Paoli S. Towards human-AI collaborative methods in UX: a qualitative case study for discovery research platforms. In BCS HCI '25: Proceedings of the 38th International BCS Human-Computer Interaction Conference. Swindon: BCS Learning & Development Ltd. 2025. p. 519-529. (Electronic Workshops in Computing (eWiC)). Epub 2025 Oct 31. doi: 10.14236/ewic/BCSHCI2025.58

Towards human-AI collaborative methods in UX: a qualitative case study for discovery research platforms

Abstract

Publication series

Conference

Keywords

Access to Document

Fingerprint

Cite this