Polarized Words, Polarized Worlds: A Computational Comparative Analysis of Pro- and Anti-Vaccine Discourse on VK

Monitoring Obshchestvennogo Mneniya: Ekonomichekie i Sotsial'nye Peremeny. 2026. No. 4. P. 50–71.

Petrov I.

This study aims to compare the emotional and thematic differences in pro-vaccination and anti-vaccination discourse on the Russian social network VKontakte (VK), using Language Expectancy Theory (LET) as an interpretive lens. A computational approach was applied to analyze 18,239 posts from 229 anti-vaccination and 84 pro-vaccination communities, utilizing dictionary-based sentiment analysis and structural topic modeling. The results revealed that anti-vaccination content is characterized by more intense use of emotional and negative language, whereas pro-vaccination communities exhibit a more neutral and rational tone. Thematically, anti-vaccination discourse more frequently focuses on children, family, and conspiracy theories, while pro-vaccination discourse emphasizes science, research, and public health efficacy. However, the emotional tone of posts was not a significant predictor of user engagement. The study identifies systematic differences in the linguistic profiles of pro- and anti-vaccination communities, consistent with expectations that LET would predict distinct audience groups. However, since this study did not directly measure persuasiveness or audience expectations, these theory-informed interpretations remain tentative and require further empirical validation.

Keywords: социальные сети, sentiment analysis, computational sociology, вероятностное тематическое моделирование, probabilistic topic modeling, social media, digital communication, вычислительная социология, анализ тональности, цифровая коммуникация, вакцинная нерешительность, vaccine hesitancy