Abstract

The exponential growth of user-generated video platforms such as YouTube has transformed the way people communicate, share opinions, and consume digital content. Among the various interaction mechanisms provided by YouTube, the comment section plays a crucial role in facilitating engagement between creators and viewers. However, the openness of this feature has also led to a significant rise in spam comments, including promotional advertisements, phishing links, misleading information, and bot-generated messages. Manual moderation of such content is impractical due to the massive volume of comments posted every minute. This paper proposes a comprehensive supervised machine learning-based framework for automatically detecting and filtering spam comments in YouTube comment sections. A publicly available dataset containing labeled YouTube comments is used for experimentation. Multiple classification algorithms, including Logistic Regression, Support Vector Machine (SVM), Decision Tree, and Artificial Neural Network (ANN), are implemented and evaluated. Extensive preprocessing and feature engineering techniques are applied to extract meaningful patterns from textual data. Experimental results demonstrate that SVM outperforms other models in terms of accuracy, precision, and F1-score. The proposed system effectively reduces the burden of human moderators while ensuring reliable and scalable spam detection. Keywords— YouTube comments, Spam filtering, Supervised machine learning, Text classification, Natural Language Processing, Support Vector Machine.