Topic Modeling in Management Research: Rendering New Theory from Textual Data

Increasingly, management researchers are using topic modeling, a new method borrowed \nfrom computer science, to reveal phenomenon-based constructs and grounded conceptual \nrelationships in textual data. By conceptualizing topic modeling as the process of rendering \nconstructs and conceptual relationships from textual data, we demonstrate how this new method \ncan advance management scholarship without turning topic modeling into a black box of \ncomplex computer-driven algorithms. We begin by comparing features of topic modeling to \nrelated techniques (content analysis, grounded theorizing, and natural language processing). We \nthen walk through the steps of rendering with topic modeling and apply rendering to \nmanagement articles that draw on topic modeling. Doing so enables us to identify and discuss \nhow topic modeling has advanced management theory in five areas: detecting novelty and \nemergence, developing inductive classification systems, understanding online audiences and \nproducts, analyzing frames and social movements, and understanding cultural dynamics. We \nconclude with a review of new topic modeling trends and revisit the role of researcher \ninterpretation in a world of computer-driven textual analysis