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

2025-05-16

AI Summary

Existing collaborative inauthentic behavior (CIB) detection methods are inadequate for video-centric platforms like TikTok, lacking multimodal, video-aware modeling. Method: We propose the first CIB detection framework tailored to video ecosystems. It integrates time-synchronized posting, AI-generated voice reuse, split-screen template replication, and overlapping hashtag/metadata sequences to construct a user behavioral similarity graph; CIB clusters are identified via graph pruning and dense subgraph detection. Contribution/Results: We empirically demonstrate that conventional signals—such as transcription-based text similarity and Duet/Stitch interactions—exhibit low discriminative power on TikTok, necessitating a video-first detection paradigm. We systematically uncover and characterize novel CIB patterns, including AI voice cloning and template reuse. Evaluated on 793K TikTok videos related to the 2024 U.S. election, our framework achieves strong generalizability and robustness. We release the first publicly available, reproducible TikTok CIB benchmark dataset and evaluation suite.

Technology Category

• Natural Language Processing: Fact-Checking / Misinformation Detection (NLP Focus)
• Computer Vision: Video Understanding & Activity Analysis
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Web Mining and Content Analysis: Large pretrained models with web data
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs

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 captions, multimedia content reuse, and hashtag sequence overlap, and apply graph pruning techniques to identify dense networks of likely coordinated accounts. Analyzing a dataset of 793K TikTok videos related to the 2024 U.S. Presidential Election, we uncover a range of coordinated activities, from synchronized amplification of political narratives to semi-automated content replication using AI-generated voiceovers and split-screen video formats. Our findings show that while traditional coordination indicators generalize well to TikTok, other signals, such as those based on textual similarity of video transcripts or Duet and Stitch interactions, prove ineffective, highlighting the platform's distinct content norms and interaction mechanics. This work provides the first empirical foundation for studying and detecting CIB on TikTok, paving the way for future research into influence operations in short-form video platforms.

Problem

• Detecting coordinated inauthentic behavior on TikTok
• Addressing gaps in video-first platform CIB detection
• Analyzing unique TikTok content and interaction structures

Innovation

• Network-based approach for TikTok CIB detection
• User similarity networks from shared behaviors
• Graph pruning to identify coordinated accounts