Topic modelling
Matthew Smith
Chapter 16 in Handbook of Research Methods and Applications in Heterodox Economics, 2026, pp 334-346 from Edward Elgar Publishing
Abstract:
This chapter introduces topic modelling as a natural language processing technique for analysing large text corpora, offering heterodox economists tools to uncover latent themes in academic literature, policy documents, and financial texts. Focusing on Latent Dirichlet Allocation (LDA), the chapter explains preprocessing steps such as tokenisation, stemming, and n-gram detection, and discusses methods for determining the optimal number of topics using metrics such as perplexity and coherence. Applications include mapping disciplinary trends, analysing corporate reports, and integrating topic modelling with sentiment analysis and social network analysis. The chapter reviews software options in R, Python, and Java (e.g., MALLET) and visualisation techniques such as word clouds and heatmaps. By enabling inductive, data-driven insights, topic modelling complements qualitative approaches and supports mixed-method research in heterodox economics.
Keywords: Topic Modelling; Text Mining; Latent Dirichlet Allocation; Heterodox Economics; Natural Language Processing; Bibliometrics (search for similar items in EconPapers)
Date: 2026
ISBN: 9781035346585
References: Add references at CitEc
Citations:
Downloads: (external link)
https://www.elgaronline.com/doi/10.4337/9781035346592.00024 (application/pdf)
Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.
Export reference: BibTeX
RIS (EndNote, ProCite, RefMan)
HTML/Text
Persistent link: https://EconPapers.repec.org/RePEc:elg:eechap:23938_17
Ordering information: This item can be ordered from
http://www.e-elgar.com
Access Statistics for this chapter
More chapters in Chapters from Edward Elgar Publishing
Bibliographic data for series maintained by Jack Sweeney ().