GPT and CLT: The impact of ChatGPT's level of abstraction on consumer recommendations
Samuel N. Kirshner
Journal of Retailing and Consumer Services, 2024, vol. 76, issue C
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.
Keywords: ChatGPT; Construal level theory; Consumer recommendations; LLMs; Bard (search for similar items in EconPapers)
Date: 2024
References: Add references at CitEc
Citations: View citations in EconPapers (2)
Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0969698923003314
Full text for ScienceDirect subscribers only
Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.
Export reference: BibTeX
RIS (EndNote, ProCite, RefMan)
HTML/Text
Persistent link: https://EconPapers.repec.org/RePEc:eee:joreco:v:76:y:2024:i:c:s0969698923003314
DOI: 10.1016/j.jretconser.2023.103580
Access Statistics for this article
Journal of Retailing and Consumer Services is currently edited by Harry Timmermans
More articles in Journal of Retailing and Consumer Services from Elsevier
Bibliographic data for series maintained by Catherine Liu (repec@elsevier.com).