Tools
Tools
Suguri Motoki, Fabio Yoshio 
ORCID: https://orcid.org/0000-0001-7464-3330, Monteiro, Januario ORCID: https://orcid.org/0000-0002-7000-4256, Malagueño, Ricardo and Rodrigues, Victor
(2023)
From Data Scarcity to Data Abundance: Crafting Synthetic Survey Data in Management Accounting using ChatGPT.
Abstract
This study examines the potential of large language models (LLMs) in generating synthetic data for survey-based research in management accounting. We propose a strategy and a framework for designing prompts and personas that enable LLMs to simulate human responses. We apply the framework to four management accounting studies and compare the statistical properties of the synthetic data with the original data. We find that LLMs can replicate human behavior and validate constructs in management accounting, addressing challenges such as survey design, construct validity, reliability, and generalizability. We also suggest that LLMs can help evaluating the epistemic relationships of constructs. In sum, LLM-generated synthetic data can be a complement to real-world data to enhance the rigor and efficiency of survey-based research.
| Item Type: | Article |
|---|---|
| Faculty \ School: | Faculty of Social Sciences > Norwich Business School |
| UEA Research Groups: | Faculty of Social Sciences > Research Groups > Accounting & Quantitative Methods |
| Related URLs: | |
| Depositing User: | LivePure Connector |
| Date Deposited: | 10 Nov 2023 01:36 |
| Last Modified: | 10 Nov 2023 01:36 |
| URI: | https://ueaeprints.uea.ac.uk/id/eprint/93615 |
| DOI: | 10.2139/ssrn.4595896 |
Actions (login required)
 |
View Item |