The geopolitics of vaccine media representation in Orbán’s Hungary—an AI‑supported sentiment analysis

In the Journal of Computational Social Science:

Extant studies on the European media coverage of the COVID-19 pandemic generally posit a linear relationship between the severity of the public health emergency and the volume of media reports. However, domestic politics and geopolitics may also impact the saliency, distribution, and sentiment of coverage in different outlets. Under Viktor Orbán’s illiberal leadership, Hungary sought deals for ventilators and vaccines from China and Russia—a deviation from joint European procurements. In this article, we conduct a content analysis of pro-government and Orbán-critical media to examine differences in their treatment of Eastern and Western vaccines.

We relied on state-of-the-art deep learning analysis (a branch of articifial intelligence) to investigate all COVID-19-related articles (N = 72,339) published on three major Hungarian news portals between March 2020 and March 2022. We used a new fine-tuned BERT model for emotion analysis, the categories of which have been aggregated into three sentiment labels (positive, negative, and neutral).

Our sentiment analysis results show a positive correlation between the number of sentences mentioning at least one of the vaccines and the (first) shots administered for only one outlet out of three. The pro-government portal in the sample showed more positivity towards Western vaccines than a hard-right, anti-government one. This latter also produced more positive reports concerning the Russian vaccine.

These results shed light on the complex geopolitics of vaccine narratives in Hungarian media. Our research contributes not only to our understanding of illiberal media systems but also by sharing a new public dataset and a fine-tuned large language model that is applicable to alternative research questions and designs.

Sebők, M., Ring, O., Kis, M.G. et al. The geopolitics of vaccine media representation in Orbán’s Hungary—an AI-supported sentiment analysis. J Comput Soc Sc (2024). https://doi.org/10.1007/s42001-024-00325-z