THETA: 一种基于文本混合嵌入的主题分析框架和AI科学家代理用于可扩展的计算社会科学
THETA: A Textual Hybrid Embedding-based Topic Analysis Framework and AI Scientist Agent for Scalable Computational Social Science
AI总结：
THETA通过Domain-Adaptive Fine-tuning优化语义向量结构，结合AI Scientist Agent框架实现主题分析的理论深度与数据规模的平衡，实验显示其在捕捉领域特定解释性构念方面优于传统模型。
摘要：
大数据的爆炸性增长使传统定性研究面临可扩展性困境，因为手动编码劳动密集且传统主题模型常出现语义稀薄和缺乏领域意识。本文介绍Textual Hybrid Embedding based Topic Analysis (THETA)，一种新的计算范式和开源工具，旨在弥合大规模数据规模与丰富理论深度之间的差距。THETA超越基于频率的统计方法，通过LoRA在基础嵌入模型上实现Domain-Adaptive Fine-tuning (DAFT)，有效优化特定社会情境中的语义向量结构以捕捉潜在意义。为确保认识论严谨性，我们将此过程封装到AI Scientist Agent框架中，包括数据管理员、建模分析师和领域专家代理，以模拟人类在循环中的专家判断和持续比较过程。脱离纯计算模型，该框架使代理能够迭代评估算法聚类、执行跨主题语义对齐，并将原始输出细化为逻辑一致的理论类别。为验证THETA的有效性，我们在六个领域，包括金融监管和公共卫生中进行了实验。我们的结果表明，THETA在捕捉领域特定解释性构念方面显著优于传统模型，如LDA、ETM和CTM，同时保持优越的连贯性。通过提供交互式分析平台，THETA使高级自然语言处理技术民主化，确保研究发现的可信度和可重复性。代码可在https://github.com/CodeSoul-co/THETA获取。
英文摘要：
The explosion of big social data has created a scalability trap for traditional qualitative research, as manual coding remains labor-intensive and conventional topic models often suffer from semantic thinning and a lack of domain awareness. This paper introduces Textual Hybrid Embedding based Topic Analysis (THETA), a novel computational paradigm and open-source tool designed to bridge the gap between massive data scale and rich theoretical depth. THETA moves beyond frequency-based statistics by implementing Domain-Adaptive Fine-tuning (DAFT) via LoRA on foundation embedding models, which effectively optimizes semantic vector structures within specific social contexts to capture latent meanings. To ensure epistemological rigor, we encapsulate this process into an AI Scientist Agent framework, comprising Data Steward, Modeling Analyst, and Domain Expert agents, to simulate the human-in-the-loop expert judgment and constant comparison processes central to grounded theory. Departing from purely computational models, this framework enables agents to iteratively evaluate algorithmic clusters, perform cross-topic semantic alignment, and refine raw outputs into logically consistent theoretical categories. To validate the effectiveness of THETA, we conducted experiments across six domains, including financial regulation and public health. Our results demonstrate that THETA significantly outperforms traditional models, such as LDA, ETM, and CTM, in capturing domain-specific interpretive constructs while maintaining superior coherence. By providing an interactive analysis platform, THETA democratizes advanced natural language processing for social scientists and ensures the trustworthiness and reproducibility of research findings. Code is available at https://github.com/CodeSoul-co/THETA.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
