Answers are grounded in this paper and cite their sources.
We propose a hybrid approach combining network analysis with advanced machine learning (ML) techniques to understand the role of social network bots in influencing political discourse. Data from the UK's 2024 public election was collected from Instagram using custom web scraping tools, subsequently anonymized, and preprocessed to ensure ethical compliance. Network analysis was conducted using centrality measures and community detection algorithms, while classic ML models including Random Forest (RF) and XGBoost (XGB) were developed and fine-tuned to detect bots and complemented with a RoBERTa model to detect AI-generated content. Interestingly, experiments show that while bots were present, they did not dominate the discussions. This suggests a strategy of subtle influence rather than overt manipulation. This finding contrasts with existing literature focused on other social media platforms, thus providing a new perspective on bot behavior and insights to mitigate the impact of bots and enhance the integrity of online political engagement.
No takes yet. Share an insight, caveat, or question.
Badami et al. (2026) studied this question.
Synapse has enriched 8 closely related papers on similar clinical questions. Consider them for comparative context: