New Tools, New Rules: A Practical Guide to Effective and Responsible Generative AI Use for Surveys and Experiments in Research
The DOI matches its Crossref record; 3 of the 3 references it cites were found in a registry or an index.
Abstract
Generative artificial intelligence (GenAI) tools based on large language models are quickly reshaping how researchers conduct surveys and experiments. From reviewing the literature and designing instruments to administering studies, coding data, and interpreting results, these tools offer substantial opportunities to improve research productivity and advance methodology. Yet with this potential comes a critical challenge: Researchers often use these systems without fully understanding how they work. This article aims to provide a practical guide for effective and responsible GenAI use in primary research. The authors begin by explaining how GenAI systems operate, highlighting the gap between their intuitive interfaces and the underlying model architectures. They then examine different use cases throughout the research process, noting both the opportunities and associated risks at each stage. Throughout this review, the authors provide flexible tips for best practice and rules for effective and responsible GenAI use, particularly in areas pertaining to ensuring the validity of GenAI-coding of unstructured data (i.e., open-ended responses). The hope is that these guidelines will help researchers integrate GenAI into their workflows in a transparent, rigorous, and ethically sound manner. An accompanying website (https://questionableresearch.ai) provides supporting materials, including reproducible coding templates in R and SPSS and sample preregistrations.
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.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“All coding decisions, theme definitions, and interpretive judgments remained the responsibility of the researcher, with AI used solely to increase efficiency in applying an established codebook (Arora et al., 2025;Blanchard et al., 2025).”
From What Competencies Should I be Teaching in my Introductory Business-to-Business Sales Course in the Age of Artificial Intelligence? (2026) · cites this paper as Blanchard et al., 2025
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 Paradigm for Developing Better Measures of Marketing Constructs
Churchill, G. A. (1979) · Journal of Marketing Research · doi:10.1177/002224377901600110 · Cited by 16,549
Simmons, J. P., Nelson, L. D., & Simonsohn, U. (2011) · Psychological Science · doi:10.1177/0956797611417632 · Cited by 6,567
GPT is an effective tool for multilingual psychological text analysis
Rathje, S., Mirea, D.-M., Sucholutsky, I., Marjieh, R., Robertson, C. E., & Van Bavel, J. J. (2024) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2308950121 · Cited by 297 · cited 2×
“GenAI-based coding (either via the API or through a custom dictionary approach) offers a more adaptive interpretation of risk language by leveraging the LLM ’ s contextual reasoning and training data (Rathje et al. 2024).”
Research works printed but not linked: 11
- 10.1177/00222429241276529 · DOI · Paper page
- 10.1002/jcpy.1453 · DOI
- 10.1016/j.jclepro.2018.02.132 · DOI
- Garvey Aaron Blanchard Simon J. (2025) “Generative AI as a Research Confederate: The LUCID Methodological Framework and Toolkit for Human-AI Interactions Research ” SSRN https://doi.org/10.2139/ssrn.5256150. · DOI
- 10.1177/0022242918816319 · DOI · Paper page
- 10.1287/mksc.2023.0454 · DOI · Paper page
- 10.1037/pspa0000449 · DOI
- 10.1177/00222437241276736 · DOI
- 10.1002/jcpy.1452 · DOI
- 10.1177/00222429251314491 · DOI · Paper page
- 10.1007/s11747-025-01097-2 · DOI
Cited by
Lin, Z. (2026) · Annual Review of Psychology · doi:10.1146/annurev-psych-100925-034807 · Cited by 4
“In the first, the LLM is a research tool—to code qualitative data, extract sentiment, generate stimuli, or assist measurement (Binz et al. 2025; Blanchard et al. 2025; Demszky et al. 2023; Feuerriegel et al. 2025; Lin 2023, 2025b; Ziems et al. 2024).”
Valdez, C. (2026) · Journal of Marketing Education · doi:10.1177/02734753261485965
Metadata
- Authors
- Blanchard, S. J., Duani, N., Garvey, A. M., Netzer, O., & Oh, T. T.
- Venue
- Journal of Marketing
- Publisher
- SAGE Publications
- Published
- 2025-09-15
- Volume
- 89
- Issue
- 6
- Pages
- 119-139
- ISSN
- 0022-2429
- 1547-7185
- Cited by
- 34
- References
- 3
- Language
- en
- Licence
- journals.sagepub.com/page/policies/text-and-data-mining-license (tdm)
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: New Tools, New Rules: A Practical Guide to Effective and Responsible Generative AI Use for Surveys and Experiments in Research. https://app.cochat.ai/papers/10.1177/00222429251349882
- The paper
- Blanchard, S. J., Duani, N., Garvey, A. M., Netzer, O., & Oh, T. T. (2025). New Tools, New Rules: A Practical Guide to Effective and Responsible Generative AI Use for Surveys and Experiments in Research. Journal of Marketing. https://doi.org/10.1177/00222429251349882
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.