Topic Modeling Hub
This is a repository for literature on and applications of the topic modeling methodology.
This page was specifically designed for the workshops on topic modeling that took place at the 2017 and 2018 Academy of Management Meeting, but is open to anyone interested.
Please see this page for a step-by-step overview of using this Github page.
The set of slides from the various presentations during the 2018 PDW can be found here.
Links to the code:
View a formatted version of the code of the 2017 PDW (discussing basic data loading, cleaning, and models) here
View a formatted version of the code of the 2018 PDW (running a basic model and showing various rendering tools) here
Much of the ideas on this page are closely intertwined with ongoing work with the organizers of the PDW, most recently expressed in our draft article prepared for the Academy of Management Annals. The abstract of this working draft can be found below. Please contact me (email@example.com) if you are interested in receiving a copy.
TOPIC MODELS IN MANAGEMENT RESEARCH: RENDERING NEW THEORY FROM BIG TEXTUAL DATA
MethodBaumer, E. P. S., Mimno, D., Guha, S., Quan, E., & Gay, G. K. (2017) Comparing grounded theory and topic modeling: Extreme divergence or unlikely convergence? Journal of the Association for Information Science and Technology 68(6), 1397–1410. doi: 10.1002/asi.23786
DiMaggio, P. (2015) Adapting computational text analysis to social science (and vice versa). Big Data & Society 2(July-December), 1–5. doi: 10.1177/2053951715602908
McFarland, D. A., Ramage, D., Chuang, J., Heer, J., Manning, C. D., & Jurafsky, D. (2013) Differentiating language usage through topic models. Journal of the Association for Information Science and Technology 41(6), 607–625. doi: 10.1016/j.poetic.2013.06.004
Mohr, J. W., & Bogdanov, P. (2013) Introduction-Topic models: What they are and why they matter. Poetics 41(6), 545–569. doi: 10.1016/j.poetic.2013.10.001
The entire special issue of the Journal of the Digital Humanities: Vol. 2, No. 1 (2012) found here. Also contains some nice videos.
ApplicationsCroidieu, G., & Kim, P. H. (Forthcoming) Labor of love: Amateurs and lay-expertise legitimation in the early U.S. radio field. Administrative Science Quarterly. doi: 10.1177/0001839216686531
DiMaggio, P., Nag, M., & Blei, D. (2013) Exploiting affinities between topic modeling and the sociological perspective on culture: Application to newspaper coverage of U.S. government arts funding. Poetics 41(6), 570–606. doi: 10.1016/j.poetic.2013.08.004
Jha, H. K., & Beckman, C. M. (2017) A patchwork of identities: Emergence of charter schools as a new organizational form. Research in the Sociology of Organizations 50, 69-107. doi: 10.1108/S0733-558X20170000050003
Kaplan, S., & Vakili, K. (2015) The double-edged sword of recombination in breakthrough innovation. Strategic Management Journal 36(10), 1435–1457. doi: 10.1002/smj.2294
Wilson, A. J., & Joseph, J. (2015) Organizational attention and technological search in the multibusiness firm: Motorola from 1974 to 1997. Advances in Strategic Management 32, 407-435. doi: 10.1108/S0742-332220150000032013
Topic modeling, a new method borrowed from computer science by management researchers, enables the processing of big (and small) textual data to help create phenomenon-based constructs and grounded conceptual relationships. In our review, we discuss precursors to topic modeling (particularly content analysis), introduce a framework for combining topic modeling analysis with theory building, examine applications of topic modeling in management research, and highlight new trends in topic modeling. Topic modeling risks being treated simply as a black-box technique that produces algorithm-generated topics from raw data, but we argue that it is most usefully understood in the context of a process for rendering constructs and conceptual relationships by combining analysis and theory. Using the rendering process as a lens enables us to categorize and evaluate the burgeoning body of topic modeling-based research articles in management and elaborate their contributions in domains ranging from framing and coherence analysis to detecting novelty and making sense of online audiences. Our goal is not only to link topic modeling method with theory building transparently, but also to engage a broader group of scholars with the topic modeling community by demonstrating topic modeling’s flexible uses.