A Novel Method for Theorising with Big Textual Data: Topic Modelling with Grounded Theory

Eyyüb Odacioglu, Lihong Zhang, Richard Allmendinger, Azar Shahgholian

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review


Recent advancements in artificial intelligence globally changed the perception on machine learning and big data applications. While the era of big data brings opportunities for practice and research, it opens a window to the possibilities to build new theories. This paper demonstrates a new method that embeds a machine learning technique into a traditional qualitative method. This method combines topic modelling with constructivist grounded theory which provides potential for contributing to theory and the knowledge reconstruction process. The study illustrates this method by analysing a corpus generated from the esteemed project management journals of the International Journal of Project Management and the Project Management Journal, identifying studies bearing on complex innovation projects. Employing topic modelling alongside the constructivist grounded theory approach, this study proceeded to analyse real-life case studies from the literature and engaged directly with Project Managers (PMs) within the aerospace industry in Turkey. This demonstration of the integrated approach guided to the establishment of a preliminary framework of Relational Accountability skill set for PMs.
Original languageEnglish
Title of host publicationAcademy of Management Proceedings
Publication statusAccepted/In press - 28 Mar 2024

Publication series

Name84th Annual Meeting of the Academy of Management Chicago 2024 Proceeding


  • Big Textual Data
  • Complex Innovation Projects
  • Grounded Theory
  • Topic Modelling
  • Relational Accountability
  • Project Management


Dive into the research topics of 'A Novel Method for Theorising with Big Textual Data: Topic Modelling with Grounded Theory'. Together they form a unique fingerprint.

Cite this