A growing interest in the study of discourses has spread in management research, but so far, it has mostly relied on in-depth qualitative analyses of textual material. With the increasing availability of large textual data, several challenges arise. This paper offers a mixed-methods approach to integrate critical discourse analysis with structural topic modeling to turn these challenges into valuable opportunities. We argue that combining both approaches overcomes their limitations and provides great potential for exploring phenomena that matter in our mediatized society. Based on an explanatory sequential mixed-methods design, we develop a stepwise model that provides practical and theoretical guidance to conduct a critical analysis of large textual data. Our illustrative example focuses on the discursive legitimation struggles around the tobacco industry. We demonstrate how an integrated mixed-methods approach allows capturing the breadth and depth of discourses used by different actors in the tobacco debates.

中文翻译：

---

从大数据到丰富的理论：将批判性话语分析与结构主题建模相结合

管理研究对话语研究的兴趣日益浓厚，但迄今为止，它主要依赖于对文本材料的深入定性分析。随着大文本数据可用性的增加，出现了一些挑战。本文提供了一种混合方法，将批判性话语分析与结构主题建模相结合，将这些挑战转化为宝贵的机会。我们认为，将这两种方法结合起来克服了它们的局限性，并为探索我们媒介化社会中重要的现象提供了巨大的潜力。基于解释性顺序混合方法设计，我们开发了一个逐步模型，该模型为对大量文本数据进行批判性分析提供了实践和理论指导。我们的说明性示例侧重于围绕烟草业的话语合法化斗争。我们展示了综合的混合方法如何能够捕捉烟草辩论中不同参与者使用的话语的广度和深度。