Integrating AI language models in qualitative research: Replicating interview data analysis with ChatGPT

Mohammad S. Jalali; Ali Akhavan

doi:10.1002/sdr.1772

journal article Open Access May 21, 2024

Integrating AI language models in qualitative research: Replicating interview data analysis with ChatGPT

Mohammad S. Jalali

Ali Akhavan

System Dynamics Review Vol. 40 No. 3 · Wiley

View at Publisher Save 10.1002/sdr.1772

Abstract

AbstractThe recent advent of artificial intelligence (AI) language tools like ChatGPT has opened up new opportunities in qualitative research. We revisited a previous project on obesity prevention interventions, where we developed a causal loop diagram through in‐depth interview data analysis. Utilizing ChatGPT in our replication process, we compared its results against our original approach. We discuss that ChatGPT contributes to improved efficiency and unbiased data processing; however, it also reveals limitations in context understanding. Our findings suggest that AI language tools currently have great potential to serve as an augmentative tool rather than a replacement for the intricate analytical tasks performed by humans. With ongoing advancements, AI technologies may soon offer more substantial support in enhancing qualitative research capabilities, an area that deserves more investigation. © 2024 The Authors. System Dynamics Review published by John Wiley & Sons Ltd on behalf of System Dynamics Society.

Topics

No keywords indexed for this article. Browse by subject →

References

29

[1]

10.1002/sdr.1773

[2]

10.1596/1813-9450-10597

[3]

10.1145/3442188.3445922

[4]

A method of analysing interview transcripts in qualitative research

Philip Burnard

Nurse Education Today 10.1016/0260-6917(91)90009-y

[5]

10.1016/j.cptl.2018.03.019

[6]

10.2196/53559

[7]

Performing an Inductive Thematic Analysis of Semi-Structured Interviews With a Large Language Model: An Exploration and Provocation on the Limits of the Approach

Stefano De Paoli

Social Science Computer Review 10.1177/08944393231220483

[8]

10.1016/j.frl.2023.103662

[9]

10.1038/s43588-023-00527-x

[10]

Holtzman A (2020)

[11]

10.3390/ijerph14080917

[12]

10.1002/sdr.1753

[13]

Jalali MS (2014)

[14]

10.1016/j.socscimed.2018.12.021

[15]

Building confidence in causal maps generated from purposive text data: mapping transcripts of the Federal Reserve

Hyunjung Kim, David F. Andersen

System Dynamics Review 10.1002/sdr.1480

[16]

10.1007/978-3-031-46002-9_1

[17]

An array of qualitative data analysis tools: A call for data analysis triangulation.

Nancy L. Leech, Anthony J. Onwuegbuzie

School Psychology Quarterly 10.1037/1045-3830.22.4.557

[18]

10.1017/dsj.2023.28

[19]

10.1002/sdr.1745

[20]

Dissecting racial bias in an algorithm used to manage the health of populations

Ziad Obermeyer, Brian Powers, Christine Vogeli et al.

Science 10.1126/science.aax2342

[21]

Rädiker S (2020)

[22]

ChatGPT: A comprehensive review on background, applications, key challenges, bias, ethics, limitations and future scope

Partha Pratim Ray

Internet of Things and Cyber-Physical Systems 10.1016/j.iotcps.2023.04.003

[23]

SapM GabrielS QinL JurafskyD SmithNA ChoiY2020.Social bias frames: reasoning about social and power implications of language. 10.18653/v1/2020.acl-main.486

[24]

An Examination of the Use of Large Language Models to Aid Analysis of Textual Data

Robert H. Tai, Lillian R. Bentley, Xin Xia et al.

International Journal of Qualitative Methods 10.1177/16094069241231168

[25]

10.1002/sdr.1701

[26]

10.1177/0894439315596311

[27]

10.1016/j.jiixd.2023.10.007

[28]

10.1145/3581754.3584136

[29]

ZhangH WuC XieJ KimC CarrollJM2023.QualiGPT: GPT as an easy‐to‐use tool for qualitative coding.

Cited By

46

Financing energy communities: Actors, instruments, builders, and ESG ecosystem expectations in Italy

Maksym Koltunov, Luca Tricarico · 2026

Energy Policy

Metrics

46

Citations

29

References

Details

Published: May 21, 2024
Vol/Issue: 40(3)
License: View

Authors

M

Mohammad S. Jalali

MGH Institute for Technology Assessment Harvard Medical School Boston Massachusetts USA; Sloan School of Management Massachusetts Institute of Technology Cambridge Massachusetts USA

A

Ali Akhavan

MGH Institute for Technology Assessment Harvard Medical School Boston Massachusetts USA

Funding

Centers for Disease Control and Prevention Award: R01CE003358

Cite This Article

Mohammad S. Jalali, Ali Akhavan (2024). Integrating AI language models in qualitative research: Replicating interview data analysis with ChatGPT. System Dynamics Review, 40(3). https://doi.org/10.1002/sdr.1772

Integrating AI language models in qualitative research: Replicating interview data analysis with ChatGPT

You May Also Like