Topic Modeling as a Strategy of Inquiry in Organizational Research: A Tutorial With an Application Example on Organizational Culture

Abstract

Research has emphasized the limitations of qualitative and quantitative approaches to studying organizational phenomena. For example, in-depth interviews are resource-intensive, while questionnaires with closed-ended questions can only measure predefined constructs. With the recent availability of large textual data sets and increased computational power, text mining has become an attractive method that has the potential to mitigate some of these limitations. Thus, we suggest applying topic modeling, a specific text mining technique, as a new and complementary strategy of inquiry to study organizational phenomena. In particular, we outline the potentials of structural topic modeling for organizational research and provide a step-by-step tutorial on how to apply it. Our application example builds on 428,492 reviews of Fortune 500 companies from the online platform Glassdoor, on which employees can evaluate organizations. We demonstrate how structural topic models allow to inductively identify topics that matter to employees and quantify their relationship with employees’ perception of organizational culture. We discuss the advantages and limitations of topic modeling as a research method and outline how future research can apply the technique to study organizational phenomena.

Virtually in this together – how web-conferencing systems enabled a new virtual togetherness during the COVID-19 crisis

“…Föll et al, 2018;Handali et al, 2020), deriving the benefits of customer service management from service request tickets , and investigating the evolution of IS research (Jeyaraj & Zadeh, 2020). Tutorials on using topic modelling in IS research (Debortoli et al, 2016;Schmiedel et al, 2019) guided the approach we applied.…”

Automated Visual Content Analysis (AVCA) in Communication Research: A Protocol for Large Scale Image Classification with Pre-Trained Computer Vision Models

“…Text-based content analysis allows researchers to segment, categorize, code, and analyze datasets automatically (Burscher et al, 2015;Kobayashi et al, 2018;Scharkow, 2013;Schmiedel et al, 2019), in response to increasingly larger (textual) datasets critical for communication research. These larger datasets require researchers to scale up their content analyses (for a discussion on the need to scale up content analysis instead of using smaller samples, see Trilling & Jonkman, 2018).…”

“…Since coding and data analysis cannot always be separated in AVCA, we regard them as one major step. Next to this classic procedure, there are two diametrical approaches to machine learning on a spectrum from inductive to deductive methodologies that this protocol covers: unsupervised versus supervised methods (Boumans & Trilling, 2016;Schmiedel et al, 2019). Figure 1 gives an overview of the protocol.…”

Mapping the Dutch Energy Transition Hyperlink Network

“…As stated by Schmiedel et al "While semantic coherence focuses on the internal qualities of single topics, exclusivity takes the similarity between different topics of the same model into account" [86] (p. 18).…”