发表机构
University of Southern Denmark（南丹麦大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出一种可审计的LLM支持的定性主题分析工作流程，推导五项设计原则，构建两阶段工作流程，经半结构化丹麦访谈记录评估，其编码覆盖与人工相当，主题更紧凑，可扩展适配不同LLM与领域。
AI 中文摘要
大语言模型（LLM）为扩大定性分析规模提供了新的可能性，但现有应用在将定性方法转化为计算程序时，往往在方法论透明度方面存在局限。本文提出了一种可审计且隐私保护的归纳式潜在主题分析（TA）的计算实现方案。首先，本文从TA的方法论要求和基于LLM推理的条件中推导得出五项设计原则：保留解释性语境、维持经验材料与分析输出间的可追溯关系、明确呈现分析构建物与推理过程、将LLM推理限制在解释性任务范围内、支持隐私保护的本地部署。其次，本文提出了一个两阶段工作流程的概念验证，该流程通过将解释性LLM推理与确定性程序控制相结合，生成编码、分析依据、主题及主题描述，同时保留与源材料的明确链接，以实现上述原则。第三，本文提出了一种评估框架，将结构比较与人工主导的TA及分析质量的独立专家评估相结合。该评估在半结构化丹麦语访谈记录上进行，结果显示，该工作流程生成的编码级输出的覆盖范围与人工注释大致相当，且分析依据获得高度评价，同时生成的主题结构更紧凑，特点是主题数量更少、范围更广。研究结果表明，通过模块化工作流程实现可审计的LLM支持TA是可行的，该工作流程可扩展至更大的数据集、适配不同的LLM，并支持跨研究领域迁移，领域适应主要需要调整提示策略。
英文摘要
Large Language Models (LLMs) offer new possibilities for scaling qualitative analysis, but existing applications often provide limited methodological transparency regarding how qualitative methods are translated into computational procedures. This paper presents an auditable and privacy-preserving computational operationalization of inductive and latent Thematic Analysis (TA). This paper first derives five design principles from the methodological requirements of TA and the conditions introduced by LLM-based inference: preserving interpretative context, maintaining traceable relationships between empirical material and analytical outputs, representing analytical constructs and reasoning explicitly, constraining LLM inference to interpretative tasks, and enabling privacy-preserving local deployment. Second, it presents a proof-of-concept for a two-phase workflow that operationalizes these principles by combining interpretative LLM inference with deterministic procedural control to generate codes, analytical justifications, themes, and theme descriptions while preserving explicit links to the source material. Third, it proposes an evaluation framework combining structural comparison with human-led TA and independent expert assessment of analytical quality. The evaluation is conducted on semi-structured Danish interview transcripts. and the results shows that the workflow produces code-level outputs with coverage broadly comparable to human annotations and highly rated analytical justifications, while generating a more compressed thematic structure characterized by fewer and broader themes. The findings demonstrate the feasibility of auditable LLM-supported TA through a modular workflow designed to scale to larger datasets, accommodate different LLMs, and support transfer across research domains, with domain adaptation primarily requiring adjustments to the prompting strategy.
