Cross-country Analysis of Political Discourse on Social media: Comparative Analysis of Topic Modeling Algorithms

Student: Bataeva Anna

Supervisor: Kirill A. Maslinsky

Faculty: Saint-Petersburg School of Social Sciences

Educational Programme: Sociology (Bachelor)

Year of Graduation: 2019

In this paper we conduct a cross-country political discourse analysis using multilingual topic modeling algorithms and comparing their results. Our methodology allows us to process multilingual cross-country corpora in order to identify current trending politics concerned topics for US, France, and Russia. We are able to do so by applying extensions of LDA for multilingual data. The results of the models are validated with parallel (TEDx transcripts) and non-parallel (politics related tweets) data. As a result of the study, we propose a methodology for conducting comparative cross-lingual discourse analysis and rank chosen multilingual model by the quality of the topics that they have produced.

Student Theses at HSE must be completed in accordance with the University Rules and regulations specified by each educational programme.

Summaries of all theses must be published and made freely available on the HSE website.

The full text of a thesis can be published in open access on the HSE website only if the authoring student (copyright holder) agrees, or, if the thesis was written by a team of students, if all the co-authors (copyright holders) agree. After a thesis is published on the HSE website, it obtains the status of an online publication.

Student theses are objects of copyright and their use is subject to limitations in accordance with the Russian Federation’s law on intellectual property.

In the event that a thesis is quoted or otherwise used, reference to the author’s name and the source of quotation is required.

Search all student theses