LLM-Assisted Content Analysis: Using Large Language Models to Support Deductive Coding

TL;DR

This paper introduces LLM-assisted content analysis (LACA), a method leveraging large language models like GPT-3.5 to make deductive coding in qualitative research faster and more reliable, with comparable accuracy to human coders.

Contribution

The study proposes and empirically evaluates LACA, demonstrating its effectiveness in reducing coding time and improving coding consistency in qualitative research.

Findings

GPT-3.5 performs deductive coding with accuracy comparable to humans.

LACA helps refine coding prompts and identify uncertain codes.

The approach guides when to use LLMs versus human coders.

Abstract

Deductive coding is a widely used qualitative research method for determining the prevalence of themes across documents. While useful, deductive coding is often burdensome and time consuming since it requires researchers to read, interpret, and reliably categorize a large body of unstructured text documents. Large language models (LLMs), like ChatGPT, are a class of quickly evolving AI tools that can perform a range of natural language processing and reasoning tasks. In this study, we explore the use of LLMs to reduce the time it takes for deductive coding while retaining the flexibility of a traditional content analysis. We outline the proposed approach, called LLM-assisted content analysis (LACA), along with an in-depth case study using GPT-3.5 for LACA on a publicly available deductive coding data set. Additionally, we conduct an empirical benchmark using LACA on 4 publicly available data sets to assess the broader question of how well GPT-3.5 performs across a range of deductive coding tasks. Overall, we find that GPT-3.5 can often perform deductive coding at levels of agreement comparable to human coders. Additionally, we demonstrate that LACA can help refine prompts for deductive coding, identify codes for which an LLM is randomly guessing, and help assess when to use LLMs vs. human coders for deductive coding. We conclude with several implications for future practice of deductive coding and related research methods.