Qualitative Analysis
Qualitative analysis, the process of interpreting non-numerical data to gain insights, is undergoing a transformation driven by advancements in large language models (LLMs). Current research focuses on leveraging LLMs for tasks like thematic analysis, topic modeling, and information extraction from diverse data sources such as interviews and social media text, often integrating them with existing qualitative methods. This integration aims to improve efficiency and scalability while addressing ethical and methodological challenges related to bias, transparency, and the role of human expertise in ensuring rigor and validity. The resulting improvements in analytical speed and depth have significant implications for various fields, including social sciences, healthcare, and software engineering.
Papers
Effectiveness of Debiasing Techniques: An Indigenous Qualitative Analysis
Vithya Yogarajan, Gillian Dobbie, Henry Gouk
Why is AI not a Panacea for Data Workers? An Interview Study on Human-AI Collaboration in Data Storytelling
Haotian Li, Yun Wang, Q. Vera Liao, Huamin Qu
Supporting Qualitative Analysis with Large Language Models: Combining Codebook with GPT-3 for Deductive Coding
Ziang Xiao, Xingdi Yuan, Q. Vera Liao, Rania Abdelghani, Pierre-Yves Oudeyer