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.
- About
Established in 2015 in collaboration with MIT Sloan Management, our vision is to be a global knowledge hub, with regional insights from Asia and the emerging world.
- Faculty & Research
ASB’s research centers conduct impactful research in emerging markets, business strategies, technology, and sustainability. Together, they foster innovation in the business landscape.
- Academics
The ASB curriculum seamlessly integrates MIT Sloan’s rigor with the strategic insights of Asia. With MIT Sloan Immersion and Industry Treks, it immerses future leaders in a diverse range of industries.
- Micro-credentials
Introducing ACE (Agile Continuous Education), a structured micro-credentials initiative offering flexible, hybrid courses developed to strengthen professional capability in a rapidly evolving landscape.
- Corporate
ASB excels through dynamic collaborations, addressing business challenges with innovation, built on robust partnerships.
AI Coding with Few-Shot Prompting for Thematic Analysis
Samuel Flanders, Melati Nungsari, Mark Cheong Wing Loong