GPT and CLT: The impact of ChatGPT's level of abstraction on consumer recommendations
Open accessThe DOI matches its Crossref record; 28 of the 28 references it cites were found in a registry or an index.
Abstract
This study explores how ChatGPT interprets information through the lens of Construal Level Theory (CLT). The findings show that ChatGPT exhibits an abstraction bias, generating responses consistent with a high-level construal. This abstraction bias results in ChatGPT prioritising high-level construal features (e.g., desirability) over low-level construal features (e.g., feasibility) in consumer evaluation scenarios. Thus, ChatGPT recommendations differ significantly from traditional results based on human decision-making. Applying CLT concepts to large language models provides essential insights into how consumer behaviour may evolve with the increasing prevalence and capability of AI and offers many promising avenues for future research.
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
Construal-level theory of psychological distance.
Trope, Y., & Liberman, N. (2010) · Psychological Review · doi:10.1037/a0018963 · Cited by 6,618
Dwivedi, Y. K., Kshetri, N., Hughes, L., Slade, E. L., Jeyaraj, A., Kar, A. K., Baabdullah, A. M., Koohang, A., Raghavan, V., Ahuja, M., et al. (2023) · International Journal of Information Management · doi:10.1016/j.ijinfomgt.2023.102642 · Cited by 4,584
Experimental evidence on the productivity effects of generative artificial intelligence
Noy, S., & Zhang, W. (2023) · Science · doi:10.1126/science.adh2586 · Cited by 2,150
What do people think they're doing? Action identification and human behavior.
Vallacher, R. R., & Wegner, D. M. (1987) · Psychological Review · doi:10.1037/0033-295x.94.1.3 · Cited by 1,802
Many Labs 2: Investigating variation in replicability across samples and settings
Klein, R. A., Vianello, M., Hasselman, F., Adams, B. G., Adams, R. B., Alper, S., Aveyard, M., Axt, J. R., Babalola, M. T., Bahník, Š., et al. (2018) · Advances in Methods and Practices in Psychological Science · doi:10.1177/2515245918810225 · Cited by 944
Out of One, Many: Using Language Models to Simulate Human Samples
Argyle, L. P., Busby, E. C., Fulda, N., Gubler, J. R., Rytting, C., & Wingate, D. (2023) · Political Analysis · doi:10.1017/pan.2023.2 · Cited by 783
Using cognitive psychology to understand GPT-3
Binz, M., & Schulz, E. (2023) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2218523120 · Cited by 559
Peres, R., Schreier, M., Schweidel, D., & Sorescu, A. (2023) · International Journal of Research in Marketing · doi:10.1016/j.ijresmar.2023.03.001 · Cited by 535
A 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
Cited by
Sarstedt, M., Adler, S. J., Rau, L., & Schmitt, B. (2024) · Psychology & Marketing · doi:10.1002/mar.21982 · Cited by 149
“Studies involving silicon sampling are scattered across numerous fields of scientific inquiry such as consumer research (e.g., Kirshner, 2024), general psychology (e.g., Caron & Srivastava, 2022), and political science (e.g., Argyle et al., 2023), making it difficult to provide a conclusive answer…”
BackgroundMarkovitch, D. G., Stough, R. A., & Huang, D. (2024) · Journal of Retailing and Consumer Services · doi:10.1016/j.jretconser.2024.103847 · Cited by 100
A Manager and an AI Walk into a Bar: Does ChatGPT Make Biased Decisions Like We Do?
Chen, Y., Kirshner, S. N., Ovchinnikov, A., Andiappan, M., & Jenkin, T. (2025) · Manufacturing & Service Operations Management · doi:10.1287/msom.2023.0279 · Cited by 143
Self-citationRiandhi, A. N., Arviansyah, M. R., & Sondari, M. C. (2025) · Cogent Business & Management · doi:10.1080/23311975.2025.2544984 · Cited by 56
“…& Cichowicz, 2024; Zhu et al., 2023) experimental studies 19 (ameen et al., 2022; Brüns & Meißner, 2024; giroux et al., 2022; t. Kim et al., 2023; Kirshner, 2024; Kovács, 2024; Letheren et al., 2021; sohn et al., 2020; Y. Zhang & Wang, 2023) Conceptual/theoretical Frameworks 17 (Bilgihan et…”
Consumer Responses to Generative AI Chatbots Versus Search Engines for Product Evaluation
Kim, S., & Priluck, R. (2025) · Journal of Theoretical and Applied Electronic Commerce Research · doi:10.3390/jtaer20020093 · Cited by 20
“ChatGPT is an AI chatbot comprising large language models (LLMs) pre-trained on an extensive amount of textual data [2], offering consumers a new way to search for information on the Internet [3].”
Metadata
- Authors
- Kirshner, S. N.
- Venue
- Journal of Retailing and Consumer Services
- Publisher
- Elsevier BV
- Published
- 2024-01
- Volume
- 76
- Pages
- 103580
- ISSN
- 0969-6989 (ISSN-L)
- OpenAlex
- W4387801424
- Cited by
- 51
- References
- 28
- FWCI
- 4.48
- Type
- journal article
- Language
- en
- Open access
- hybrid
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: GPT and CLT: The impact of ChatGPT's level of abstraction on consumer recommendations. https://app.cochat.ai/papers/10.1016/j.jretconser.2023.103580
- The paper
- Kirshner, S. N. (2024). GPT and CLT: The impact of ChatGPT's level of abstraction on consumer recommendations. Journal of Retailing and Consumer Services. https://doi.org/10.1016/j.jretconser.2023.103580
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.