Privacy Preserving Topic-wise Sentiment Analysis of the Iran Israel USA Conflict Using Federated Transformer Models

2026-03-13

AI Summary

This study addresses the challenge of analyzing public sentiment at the topic level regarding the Iran–Israel–U.S. conflict on global social media while preserving user privacy. To this end, we propose a novel framework that integrates topic modeling (LDA), transformer-based sentiment classification—leveraging fine-tuned BERT, RoBERTa, and ELECTRA models—and federated learning, augmented with SHAP for model interpretability. Experimental results demonstrate that ELECTRA achieves an accuracy of 91.32% in a centralized setting and maintains strong performance at 89.59% under a two-client federated learning configuration. This approach effectively balances data privacy, analytical accuracy, and decision transparency, offering a robust solution for privacy-conscious social media analysis in geopolitically sensitive contexts.

Technology Category

• Machine Learning: Privacy
• Natural Language Processing: Ethics — Bias, Fairness, Transparency & Privacy
• Computer Vision: Bias, Fairness & Privacy

Application Category

• Web Mining and Content Analysis: Large pretrained models with web data
• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Social Networks and Social Media: Fairness and bias in social network and social media analysis

Abstract

The recent escalation of the Iran Israel USA conflict in 2026 has triggered widespread global discussions across social media platforms. As people increasingly use these platforms for expressing opinions, analyzing public sentiment from these discussions can provide valuable insights into global public perception. This study aims to analyze global public sentiment regarding the Iran Israel USA conflict by mining user-generated comments from YouTube news channels. The work contributes to public opinion analysis by introducing a privacy preserving framework that combines topic wise sentiment analysis with modern deep learning techniques and Federated Learning. To achieve this, approximately 19,000 YouTube comments were collected from major international news channels and preprocessed to remove noise and normalize text. Sentiment labels were initially generated using the VADER sentiment analyzer and later validated through manual inspection to improve reliability. Latent Dirichlet Allocation (LDA) was applied to identify key discussion topics related to the conflict. Several transformer-based models, including BERT, RoBERTa, XLNet, DistilBERT, ModernBERT, and ELECTRA, were fine tuned for sentiment classification. The best-performing model was further integrated into a federated learning environment to enable distributed training by preserving user data privacy. Additionally, Explainable Artificial Intelligence (XAI) techniques using SHAP were applied to interpret model predictions and identify influential words affecting sentiment classification. Experimental results demonstrate that transformer models perform effectively, and among them, ELECTRA achieved the best performance with 91.32% accuracy. The federated learning also maintained strong performance while preserving privacy, achieving 89.59% accuracy in a two client configuration.

Problem

• Privacy Preserving
• Topic-wise Sentiment Analysis
• Iran Israel USA Conflict
• Federated Learning
• Social Media

Innovation

• Federated Learning
• Transformer Models
• Privacy Preservation
• Topic-wise Sentiment Analysis
• Explainable AI (XAI)