Coordinated Inauthentic Behavior on TikTok: Challenges and Opportunities for Detection in a Video-First Ecosystem

Abstract

Detecting coordinated inauthentic behavior (CIB) is central to the study of online influence operations. However, most methods focus on text-centric platforms, leaving video-first ecosystems like TikTok largely unexplored. To address this gap, we develop and evaluate a computational framework for detecting CIB on TikTok, leveraging a network-based approach adapted to the platform’s unique content and interaction structures. Building on existing approaches, we construct user similarity networks based on shared behaviors, including synchronized posting, repeated use of similar speech segments, and multimedia content reuse, and apply graph pruning techniques to identify dense networks of likely coordinated accounts. Analyzing a dataset of 1.35M TikTok videos related to the 2024 U.S. Presidential Election, we uncover a range of coordinated activities, from synchronized amplification of political narratives and semi-automated content replication to AI-generated voiceovers and manufactured split-screen video formats. Our findings demonstrate that while several indicators proposed in this study effectively detect CIB on TikTok, other platform-native signals, such as video-based replies and Duet and Stitch interactions, often reflect organic engagement rather than inauthentic behavior, highlighting the platform’s distinct content dynamics and interaction mechanics. This work provides the first empirical foundation for studying CIB on TikTok, paving the way for future research into influence operations on video platforms.