2025/02/16 by Zhen Tan, Zhao, Chengshuai, Tan, Zhen +8 · 2 citations
Social Sciences · #Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #Computational and Text Analysis Methods #FOS: Computer and information sciences #Multiagent Systems (cs.MA)
paper · pdf · doi:10.48550/arxiv.2502.10937
openalex publication_date 2025/02/16 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/30
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 \underlineSimulates \underlineContent \underlineAnalysis via \underlineLarge language model (LLM) ag\underlineEnts. 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.