Studying Behavioral Addiction by Combining Surveys and Digital Traces: A Case Study of TikTok

2025-01-26

AI Summary

This study addresses the diagnostic feasibility of digital addiction among TikTok users. We propose a hybrid validation paradigm integrating large-scale survey data (N=1,590) with real-world behavioral logs (N=107). For the first time on a short-video platform, we empirically identify temporal behavioral patterns characteristic of addicted users—such as high-frequency revisits and sustained daytime engagement—and establish a hierarchical behavioral analytics framework grounded in viewing duration, visit frequency, and session inter-arrival intervals. Using temporal pattern mining and binary classification modeling, we achieve effective identification of high-risk users (F1 ≥ 0.55), yet uncover an inherent prediction ceiling (~0.55 F1) when relying solely on surface-level engagement metrics. Key contributions include: (1) establishing empirically grounded diagnostic criteria for behavioral addiction in the TikTok context; (2) revealing fundamental limitations of pure behavioral-data-driven prediction; and (3) providing an actionable, behaviorally anchored risk identification pathway for digital well-being interventions.

Technology Category

• Data Mining & Knowledge Management: Mining of Spatial, Temporal or Spatio-Temporal Data
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning
• Application Domains: Humanities & Computational Social Science

Application Category

• User Modeling, Personalization and Recommendation: Metrics for user behavior and evaluating success
• Web Mining and Content Analysis: Web data quality in the era of algorithmically-generated content
• Responsible Web: Data and user privacy-enhancing technologies for the Web

Abstract

Opaque algorithms disseminate and mediate the content that users consume on online social media platforms. This algorithmic mediation serves users with contents of their liking, on the other hand, it may cause several inadvertent risks to society at scale. While some of these risks, e.g., filter bubbles or dissemination of hateful content, are well studied in the community, behavioral addiction, designated by the Digital Services Act (DSA) as a potential systemic risk, has been understudied. In this work, we aim to study if one can effectively diagnose behavioral addiction using digital data traces from social media platforms. Focusing on the TikTok short-format video platform as a case study, we employ a novel mixed methodology of combining survey responses with data donations of behavioral traces. We survey 1590 TikTok users and stratify them into three addiction groups (i.e., less/moderately/highly likely addicted). Then, we obtain data donations from 107 surveyed participants. By analyzing users' data we find that, among others, highly likely addicted users spend more time watching TikTok videos and keep coming back to TikTok throughout the day, indicating a compulsion to use the platform. Finally, by using basic user engagement features, we train classifier models to identify highly likely addicted users with $F_1 geq 0.55$. The performance of the classifier models suggests predicting addictive users solely based on their usage is rather difficult.

Problem

• Digital Addiction
• Social Media Behavior
• TikTok Users

Innovation

• Digital Addiction
• TikTok User Behavior
• Predictive Modeling