FL-XGBTC: federated learning inspired with XG-boost tuned classifier for YouTube spam content detection

Abstract

The problem of spam content in YouTube comments is an ongoing issue, and detecting such content is a critical task to maintain the quality of user experience on the platform. In this study, we propose a Federated Learning Inspired XG-Boost Tuned Classifier, FL-XGBTC, for YouTube spam content detection. The proposed model leverages the advantages of federated learning, which enables the training of a model collaboratively across multiple devices without sharing raw data. The FL-XGBTC model is based on the XGBoost algorithm, which is a powerful and widely used ensemble learning algorithm for classification tasks. The proposed model was trained on a large and diverse dataset of YouTube comments, which includes both spam and non-spam comments. The results demonstrate that the FL-XGBTC model achieved a high level of accuracy in detecting spam content in YouTube comments, outperforming several baseline models. Additionally, the proposed model provides the benefit of preserving user privacy, which is a critical consideration in modern machine-learning applications. Overall, the proposed Federated Learning Inspired XG-Boost Tuned Classifier provides a promising solution for YouTube spam content detection that leverages the benefits of federated learning and ensemble learning algorithms. The major contribution of this work is to demonstrate and propose a framework for showing a distributed federated classifier for the multiscale classification of youtube spam comments using the Ensemble learning method.