Me and the Machines: Possibilities and Pitfalls of Using Artificial Intelligence for Qualitative Data Analysis
Open accessThe DOI matches its Crossref record; 7 of the 7 references it cites were found in a registry or an index.
Abstract
This paper describes how one researcher learned to overcome artificial intelligence (AI) paralysis and embrace ChatPDF. This freely available AI application uses natural language processing (NLP) to respond to user queries about an uploaded PDF. Researcher insights from experimenting with the AI tool ChatPDF for qualitative data analysis are presented, highlighting the advantages, pitfalls, and application-related considerations. As a two-phase curiosity experiment, the researcher engaged in a theory-building exercise to explore key concepts for understanding when using ChatPDF to assist researchers in qualitative data analysis. The experiment generated insights about the purposeful use of AI tools that incorporate NLP for analysis and the risks of inaccuracy when researchers are not familiar with the data or skilled in prompt engineering. Insights raise questions about whether ChatPDF is a viable research assistant for qualitative researchers, ethical issues with specific forms of qualitative data, and the potential of AI tools for community and student researchers.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
A Prompt Pattern Catalog to Enhance Prompt Engineering with ChatGPT
White, J., Fu, Q., Hays, S., Sandborn, M., Olea, C., Gilbert, H., Elnashar, A., Spencer-Smith, J., & Schmidt, D. C. (2023) · arXiv · doi:10.48550/arxiv.2302.11382 · Cited by 838
Kuleto, V., Ilić, M., Dumangiu, M., Ranković, M., Martins, O. M. D., Păun, D., & Mihoreanu, L. (2021) · Sustainability · doi:10.3390/su131810424 · Cited by 561 · cited 1×
“Building on previous insights about the value of AI in higher education institutions (Kuleto et al., 2021; Ma & Siau, 2018) the potential for AI-assisted QDA demonstrated in this ex-periment should initiate “ how might we ” conversations be-tween community – university partnerships for upscaling…”
BackgroundA Categorical Archive of ChatGPT Failures
Borji, A. (2023) · doi:10.21203/rs.3.rs-2895792/v1 · Cited by 514
A Categorical Archive of ChatGPT Failures
Borji, A. (2023) · arXiv · doi:10.48550/arxiv.2302.03494 · Cited by 514
Educational Research and AI-Generated Writing: Confronting the Coming Tsunami
Tate, T. P., Doroudi, S., Ritchie, D., Xu, Y., & uci, M. W. (2023) · doi:10.35542/osf.io/4mec3 · Cited by 137
Artificial Intelligence-Enabled Science Poetry
Kirmani, A. R. (2023) · ACS Energy Letters · doi:10.1021/acsenergylett.2c02758 · Cited by 124
Fang, C., Markuzon, N., Patel, N., & Rueda, J.-D. (2022) · Value in Health · doi:10.1016/j.jval.2022.06.004 · Cited by 36 · cited 1×
“…have investigated the potential of using NLP models to perform a variety of non-automated and automated analytical functions aiding the QDA process (Ancheta et al., 2020; Cheligeer et al., 2022; Fang et al., 2022; Guetterman et al., 2018; Leeson et al., 2019; Perrin, 2001; Skeen et al., 2022).”
Method
Research works printed but not linked: 50
- 10.1080/14616734.2018.1429477 · DOI
- 10.1109/KST48564.2020.9059411 · DOI
- 10.1007/s10439-023-03171-8 · DOI · Paper page
- 10.1177/1077800411409885 · DOI · Paper page
- 10.1080/13603116.2019.1588926 · DOI
- Bozkurt A., 2023, Asian Journal of Distance Education, 18
- Candela A. G., 2019, The Qualitative Report, 24, 619
- ChatPDF, FAQs
- 10.3233/JID-220013 · DOI
- Clarke A. B., 1980, Omni Magazine, 2, 76
- 10.1080/13645579.2011.625764 · DOI · Paper page
- Fader N., 2020, Journal of Park and Recreation Administration, 38
- Gray T., 2019, Exploring ways to elevate women’s leadership voices to achieve career longevity and gender parity
- 10.2196/jmir.9702 · DOI · Paper page
- Hosseini M., 2023, Research Integrity and Peer Review, 8, 1
- Islam I., 2023, Opportunities and challenges of ChatGPT in academia: A conceptual analysis
- 10.1080/17457823.2013.828475 · DOI
- 10.1080/09575146.2022.2031120 · DOI
- Kraugusteeliana K., 2023, Journal Pendidikan dan Konseling, 5, 3245
- 10.1080/17408989.2019.1700496 · DOI
- Leeson W., 2019, International Journal of Qualitative Methods, 18
- 10.1007/978-3-030-31787-4_1 · DOI
- Ma Y., Siau K. L. (2018). Artificial intelligence impacts on higher education. MWAS 2019 Proceedings, May 17 – 18, 2018, College St. Louis of Business Administration, University of Missouri –, 42. https://aisel.aisnet.org/mwais2018/42
- 10.1080/1369118X.2019.1602665 · DOI
- 10.1080/14999013.2018.1531095 · DOI
- Miles M. B., 2014, Qualitative data analysis: A methods sourcebook
- 10.1007/978-3-030-16065-4_25 · DOI
- 10.1371/journal.pone.0153749 · DOI · Paper page
- 10.1123/iscj.2018-0085 · DOI
- 10.1080/13645579.2021.2018905 · DOI
- 10.1177/089443930101900207 · DOI
- 10.1108/S0733-558X20190000059011 · DOI
- Riessman C. K., 2008, Narrative methods for the human sciences
- 10.1177/1468794118816618 · DOI
- 10.31219/osf.io/9xkbu · DOI
- 10.2196/37350 · DOI
- Soares N. M., 2019, An inside and an outside: Young people in care who run away. A psychoanalytic approach
- 10.1109/APR59189.2023.00012 · DOI · Paper page
- 10.1177/1049732307306187 · DOI · Paper page
- 10.3109/13561820.2014.911157 · DOI
- Tabone W., 2023, Using ChatGPT for human–computer interaction research: A primer, 10.1098/rsos.231053 · DOI
- 10.3390/electronics12091964 · DOI
- 10.36931/jma.2020.2.2.83-99 · doi:10.36931/jma.2020.2.2.83-99
- 10.1002/ctm2.1207 · DOI
- 10.1038/d41586-019-02871-3 · DOI
- Wulf F., 2021, IaaS, PaaS, or SaaS? The why of cloud computing delivery model selection: Vignettes on the post-adoption of cloud computing, 6285
- 10.1111/epi.17474 · DOI
- Zhong Q., 2023, Can ChatGPT understand too? A comparative study on ChatGPT and fine-tuned BERT
- Zhuo T. Y., 2023, Exploring ai ethics of ChatGPT: A diagnostic analysis
- Zuccon G., 2023, Dr ChatGPT, tell me what I want to hear: How prompt knowledge impacts health answer correctness
Cited by
Qualitative Research in the Era of AI: A Return to Positivism or a New Paradigm?
Chatzichristos, G. (2025) · International Journal of Qualitative Methods · doi:10.1177/16094069251337583 · Cited by 34
AI Voice Methodology: Using Generative AI in Qualitative Social Research
Hughes, J., Homan, L., O’Reilly, M., & Hughes, K. (2025) · Qualitative Inquiry · doi:10.1177/10778004251401842 · Cited by 2
Metadata
- Authors
- Chubb, L. A.
- Venue
- International Journal of Qualitative Methods
- Publisher
- SAGE Publications
- Published
- 2023-09-08
- Volume
- 22
- ISSN
- 1609-4069 (ISSN-L)
- OpenAlex
- W4386549317
- Cited by
- 65
- References
- 7
- FWCI
- 31.40
- Type
- journal article
- Language
- en
- Open access
- gold
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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Me and the Machines: Possibilities and Pitfalls of Using Artificial Intelligence for Qualitative Data Analysis. https://app.cochat.ai/papers/10.1177/16094069231193593
- The paper
- Chubb, L. A. (2023). Me and the Machines: Possibilities and Pitfalls of Using Artificial Intelligence for Qualitative Data Analysis. International Journal of Qualitative Methods. https://doi.org/10.1177/16094069231193593
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.