Reflections on Inductive Thematic Saturation as a potential metric for measuring the validity of an inductive Thematic Analysis with LLMs

TL;DR

This paper explores using initial thematic saturation as a metric to evaluate the validity of inductive thematic analysis performed by Large Language Models, proposing a new quantitative approach for assessing coding saturation.

Contribution

It introduces a novel metric based on saturation ratios to measure the initial coding validity of LLMs in thematic analysis, advancing qualitative analysis with AI.

Findings

LLMs reach a form of analytical saturation during initial coding.

A new metric based on code saturation ratios is proposed.

The procedure produces two comprehensive codebooks.

Abstract

This paper presents a set of reflections on saturation and the use of Large Language Models (LLMs) for performing Thematic Analysis (TA). The paper suggests that initial thematic saturation (ITS) could be used as a metric to assess part of the transactional validity of TA with LLM, focusing on the initial coding. The paper presents the initial coding of two datasets of different sizes, and it reflects on how the LLM reaches some form of analytical saturation during the coding. The procedure proposed in this work leads to the creation of two codebooks, one comprising the total cumulative initial codes and the other the total unique codes. The paper proposes a metric to synthetically measure ITS using a simple mathematical calculation employing the ratio between slopes of cumulative codes and unique codes. The paper contributes to the initial body of work exploring how to perform qualitative analysis with LLMs.