SCALE: Towards Collaborative Content Analysis in Social Science with Large Language Model Agents and Human Intervention
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866917267599523840 |
|---|---|
| author | Zhao, Chengshuai Tan, Zhen Wong, Chau-Wai Zhao, Xinyan Chen, Tianlong Liu, Huan |
| author_facet | Zhao, Chengshuai Tan, Zhen Wong, Chau-Wai Zhao, Xinyan Chen, Tianlong Liu, Huan |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_10937 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | SCALE: Towards Collaborative Content Analysis in Social Science with Large Language Model Agents and Human Intervention Zhao, Chengshuai Tan, Zhen Wong, Chau-Wai Zhao, Xinyan Chen, Tianlong Liu, Huan Artificial Intelligence Computation and Language Multiagent Systems 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. |
| title | SCALE: Towards Collaborative Content Analysis in Social Science with Large Language Model Agents and Human Intervention |
| topic | Artificial Intelligence Computation and Language Multiagent Systems |
| url | https://arxiv.org/abs/2502.10937 |