AI Coding with Few-Shot Prompting for Thematic Analysis
This addresses the challenge for researchers who need to conduct exhaustive thematic analyses on large corpora but find manual coding infeasible, though it is incremental as it builds on existing LLM techniques.
The paper tackled the labor-intensive problem of coding for thematic analysis by using GPT 3.5-Turbo with few-shot prompting to generate higher quality codes on semantically similar passages, resulting in a more scalable and cost-effective method.
This paper explores the use of large language models (LLMs), here represented by GPT 3.5-Turbo to perform coding for a thematic analysis. Coding is highly labor intensive, making it infeasible for most researchers to conduct exhaustive thematic analyses of large corpora. We utilize few-shot prompting with higher quality codes generated on semantically similar passages to enhance the quality of the codes while utilizing a cheap, more easily scalable model.