MTikGuard System: A Transformer-Based Multimodal System for Child-Safe Content Moderation on TikTok

TL;DR

MTikGuard is a real-time, multimodal content moderation system for TikTok that combines an expanded dataset, advanced fusion techniques, and scalable architecture to effectively detect harmful content targeting children.

Contribution

The paper introduces an extended TikHarm dataset, a novel multimodal classification framework, and a scalable streaming architecture for real-time harmful content detection on TikTok.

Findings

Achieved 89.37% accuracy and 89.45% F1-score in harmful content detection.

Expanded dataset with 4,723 labeled videos including diverse real-world samples.

Demonstrated effective deployment of multimodal fusion in a scalable streaming system.

Abstract

With the rapid rise of short-form videos, TikTok has become one of the most influential platforms among children and teenagers, but also a source of harmful content that can affect their perception and behavior. Such content, often subtle or deceptive, challenges traditional moderation methods due to the massive volume and real-time nature of uploads. This paper presents MTikGuard, a real-time multimodal harmful content detection system for TikTok, with three key contributions: (1) an extended TikHarm dataset expanded to 4,723 labeled videos by adding diverse real-world samples, (2) a multimodal classification framework integrating visual, audio, and textual features to achieve state-of-the-art performance with 89.37% accuracy and 89.45% F1-score, and (3) a scalable streaming architecture built on Apache Kafka and Apache Spark for real-time deployment. The results demonstrate the effectiveness of combining dataset expansion, advanced multimodal fusion, and robust deployment for practical large-scale social media content moderation. The dataset is available at https://github.com/ntdat-8324/MTikGuard-System.git.