CollabCoder：一种利用大语言模型开展归纳式协作质性分析的低门槛、严谨工作流
CollabCoder: A Lower-barrier, Rigorous Workflow for Inductive Collaborative Qualitative Analysis with Large Language Models
AI总结：
本文提出 CollabCoder 工作流，将 LLMs 融入归纳式协作质性分析的开放编码、讨论与编码簿构建环节，并经 16 名用户评估验证其低门槛、有效性及相对现有软件的优势。
摘要：
协作质性分析（Collaborative Qualitative Analysis, CQA）能够通过纳入多元观点来提升质性分析的严谨性与深度。然而，确保严谨的 CQA 过程本身既费力又昂贵。为降低这一门槛，我们从理论视角出发设计了 CollabCoder 工作流，将大语言模型（Large Language Models, LLMs）整合到归纳式 CQA 的关键阶段：独立开放编码、迭代讨论以及最终编码簿创建。在开放编码阶段，CollabCoder 提供 AI 生成的代码建议，并记录决策数据。在讨论过程中，它通过在编码团队内共享这些数据，并使用量化指标识别编码的一致与分歧，促进相互理解，从而协助达成共识。在代码分组阶段，CollabCoder 提供初步代码分组建议，减轻最终确定编码簿的认知负荷。一项包含 16 名用户的评估证实了 CollabCoder 的有效性，展示了其相较现有软件的优势，并提供了关于 LLMs 在 CQA 实践中作用的经验性洞见。
英文摘要：
Collaborative Qualitative Analysis (CQA) can enhance qualitative analysis rigor and depth by incorporating varied viewpoints. Nevertheless, ensuring a rigorous CQA procedure itself can be both demanding and costly. To lower this bar, we take a theoretical perspective to design the CollabCoder workflow, that integrates Large Language Models (LLMs) into key inductive CQA stages: independent open coding, iterative discussions, and final codebook creation. In the open coding phase, CollabCoder offers AI-generated code suggestions and records decision-making data. During discussions, it promotes mutual understanding by sharing this data within the coding team and using quantitative metrics to identify coding (dis)agreements, aiding in consensus-building. In the code grouping stage, CollabCoder provides primary code group suggestions, lightening the cognitive load of finalizing the codebook. A 16-user evaluation confirmed the effectiveness of CollabCoder, demonstrating its advantages over existing software and providing empirical insights into the role of LLMs in the CQA practice.
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。
