Health Discourse Regarding Syrian Refugees in Türkiye on Twitter: A Longitudinal Sentiment and Stance Analysis Study (Preprint)
Abstract
BACKGROUND Since 2011, Türkiye has become the primary destination for Syrian refugees. While healthcare is a fundamental human right, public discourse surrounding refugee health services can influence policy and social cohesion. OBJECTIVE The objective of our study was to examine 14 years of Turkish health-related discourse on platform X (formerly Twitter) to identify evolving sentiment, stance, and key grievances. METHODS From a dataset of 4.5 million tweets (2009-2022), 116,172 health-related posts were identified. We employed a fine-tuned Turkish BERT-based large language model to perform multi-task classification for sentiment, stance, and health topics. Tweets were categorized into five domains as Provision of Healthcare Services, Financing and Coverage, Human Resources, Public Health and Disease Prevention, and Access to Medications and Pharmaceutical Services. Lift scores and heatmaps were used to analyze the relationship between the keywords and public attitudes. RESULTS The fine-tuned Turkish BERT model achieved high classification performance with a weighted F1 score of 0.85 for sentiment and 0.8 for stance detection. Public discourse shifted from neutral or positive tones in 2011 to overwhelming negativity over time. By 2021, negative sentiment reached 79.9%, and anti-refugee stance peaked at 78.3%. Prominent topics evolved from Provision of Healthcare Services (47.5% in 2011) to Public Health and Disease Prevention (57.3% in 2021) and Human Resources (34.6% in 2022). High lift scores revealed that anti-refugee stances were strongly associated with keywords such as ‘appointment’, ‘vaccine’, and ‘free’. CONCLUSIONS There is a marked and consistent rise in anti-refugee sentiment within Turkish digital health discourse, often fueled by misinformation and perceived systemic strain. Public health authorities should prioritize evidence-based communication strategies to counter digital polarization and ensure the legibility of health policies for the host population.
Fields of Study & Subjects
Sentiment Analysis and Opinion Mining
Migration
Racism
and Human Rights
Refugees
and Integration
Publication details
- Publication date
- 10 February 2026
- Language
- EN
- Document type
- Preprint