Auditing Algorithmic Personalization in TikTok Comment Sections

2026-03-26

AI Summary

This study presents the first systematic audit of whether TikTok’s comment ranking algorithm personalizes content based on users’ political orientations and how such personalization affects exposure to diverse viewpoints. By creating simulated accounts with distinct left- and right-leaning political profiles and collecting comments under identical neutral political videos, the authors analyze differences in comment visibility across ideological groups. The findings reveal significant divergence in the comments displayed to differently aligned accounts for certain videos. This polarization in comment exposure is closely associated with factors including total comment volume, inequality in user engagement, and the partisan skew of the comment section. The results provide preliminary evidence that TikTok employs a politically aligned comment exposure mechanism, whose effects are context-dependent.

Technology Category

• Machine Learning: Learning Preferences or Rankings
• Natural Language Processing: Ethics — Bias, Fairness, Transparency & Privacy
• Computer Vision: Bias, Fairness & Privacy

Application Category

• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Social Networks and Social Media: Media and governance, opinion dynamics, filter bubbles, polarization
• Responsible Web: Algorithmic accountability and transparency on the web

Abstract

Personalization algorithms are ubiquitous in modern social computing systems, yet their effects on comment sections remain underexplored. In this work, we conducted an algorithmic auditing experiment to examine comment personalization on TikTok. We trained sock-puppet accounts to exhibit left-leaning or right-leaning preferences and successfully validated 17 of them by analyzing the videos recommended on their For You Pages. We then scraped the comment sections shown to these trained partisan accounts, along with five cold-start accounts, across 65 politically neutral videos related to the 2024 U.S. presidential election that contain abundant discussions from both left-leaning and right-leaning perspectives. We find that while the composition of top comments remains largely consistent for all videos, ranking divergence between accounts from different political groups is significantly greater than that observed within the same group for some videos. This effect is strongly correlated with video-level metrics such as comment volume, engagement inequality, and partisan skew in the comment sections. Furthermore, through an exploratory case study, we find preliminary evidence that personalization can result in comment exposure aligned with an account's political leaning. However, this pattern is not universal, suggesting that the extent of politically oriented comment personalization is context-dependent.

Problem

• algorithmic personalization
• comment sections
• political bias
• social media auditing
• TikTok

Innovation

• algorithmic auditing
• comment personalization
• sock-puppet accounts
• political bias
• social media algorithms