SCALE: Towards Collaborative Content Analysis in Social Science with Large Language Model Agents and Human Intervention

TL;DR

SCALE introduces a multi-agent framework utilizing large language models and human intervention to automate and improve complex content analysis in social science, mimicking human coding, discussion, and codebook evolution.

Contribution

This paper presents SCALE, a novel multi-agent system that simulates human-like content analysis processes with LLMs and human input, advancing automation in social science research.

Findings

SCALE achieves performance comparable to human annotators.

The framework effectively models collaborative discussion and codebook evolution.

Incorporating human intervention enhances analysis accuracy.

Abstract

Content analysis breaks down complex and unstructured texts into theory-informed numerical categories. Particularly, in social science, this process usually relies on multiple rounds of manual annotation, domain expert discussion, and rule-based refinement. In this paper, we introduce SCALE, a novel multi-agent framework that effectively $\underline{\textbf{S}}$imulates $\underline{\textbf{C}}$ontent $\underline{\textbf{A}}$nalysis via $\underline{\textbf{L}}$arge language model (LLM) ag$\underline{\textbf{E}}$nts. SCALE imitates key phases of content analysis, including text coding, collaborative discussion, and dynamic codebook evolution, capturing the reflective depth and adaptive discussions of human researchers. Furthermore, by integrating diverse modes of human intervention, SCALE is augmented with expert input to further enhance its performance. Extensive evaluations on real-world datasets demonstrate that SCALE achieves human-approximated performance across various complex content analysis tasks, offering an innovative potential for future social science research.