Federated Learning (FL) is transforming social media analytics by enabling privacy- preserving data analysis across distributed platforms. However, traditional analytics methods face major challenges due to data privacy concerns and centralized data collection. FL addresses these issues by allowing model training without sharing raw user data, making analytics more secure and reliable. This paper presents a review of FL in social media analytics, focusing on its importance, techniques, and applications. FL methods such as secure aggregation and differential privacy help analyze user engagement, content trends, and creator performance while protecting user data. These approaches also reduce risks related to privacy, bias, and ethical concerns. Implementing FL in social media analytics helps build user trust, ensures compliance with regulations, and improves data-driven decision-making.
Yashvi et al. (Thu,) studied this question.