Monday, 20 January, 2020 - 14:00

A Case Study of Using LDA Topic Modeling in Sociological Research – Antisemitism in Contemporary Hungary

Ildikó Barna

The availability of large volumes of unstructured digital textual data set new challenges for social research as the processing of digital textual data requires new methodological tools; Natural Language Processing (NLP) is being one of them. Sociologists have an important role when NLP is used in social-related topics as they can provide the domain knowledge that is necessary to link the analysis to sociological discourses by forming sociologically relevant research questions and hypotheses, defining relevant variables, and interpreting the results in the larger theoretical context.
In 2019, at ELTE University Faculty of Social Sciences, in one of the working groups of the Research Center for Computational Social Science (, we analyzed overt online antisemitism using LDA topic modeling. The aim of the lecture is two-fold. On the one hand, it aims at presenting the results of this analysis. On the other hand, it aims at demonstrating how sociology can be utilized for the interpretation of the results of NLP.


Ildikó BARNA is a sociologist. She is an Associate Professor at ELTE University Faculty of Social Sciences Budapest, where she also serves as Head of the Department of Social Research Methodology. Her research topics include antisemitism, xenophobia, post-Holocaust studies, and quantitative research on archival sources. Recently, her interest turned to the research of online hate speech using automated text analysis. Ildikó Barna is currently the fellow of the János Bolyai Research Fellowship of the Hungarian Academy of Sciences.