From Big Data to Rich Theory: Integrating Critical Discourse Analysis with Structural Topic Modeling

Ana M. Aranda, Kathrin Sele*, Helen Etchanchu, Jonne Y. Guyt, Eero Vaara

*Corresponding author for this work

Research output: Contribution to JournalArticleAcademicpeer-review

Abstract

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.

Original languageEnglish
Pages (from-to)197-214
Number of pages18
JournalEuropean Management Review
Volume18
Issue number3
Early online date7 May 2021
DOIs
Publication statusPublished - Sep 2021

Bibliographical note

Funding Information:
This research has been supported by the Academy of Finland, grant numbers 315665 and 321362.

Publisher Copyright:
© 2021 The Authors. European Management Review published by John Wiley & Sons Ltd on behalf of European Academy of Management (EURAM)

Keywords

  • critical discourse analysis
  • mixed methods
  • structural topic modeling

Fingerprint

Dive into the research topics of 'From Big Data to Rich Theory: Integrating Critical Discourse Analysis with Structural Topic Modeling'. Together they form a unique fingerprint.

Cite this