Northwestern University researchers found that TikTok's algorithm inadequately responds to negative user feedback. Despite users expressing disinterest, suggested videos often remain on their For You Page, limiting their perceived control over content curation.
Researchers from Northwestern University conducted an audit of TikTok's algorithm to evaluate user feedback mechanisms. They aimed to understand the platform's responsiveness to negative input, following user reports of dissatisfaction with content persistence despite disinterest indications.
The researchers created bot accounts on TikTok and interfaced with the platform's algorithm to analyze content delivery. They intercepted network traffic to gather metadata and utilized a machine learning model to simulate user responses, allowing for controlled experimentation on feedback impact.
The study revealed that while engagement signals do influence the algorithm, their effect diminishes over time. Users' attempts to curate their feeds through the 'not interested' feature do not consistently yield long-term changes, raising concerns about user agency.
The findings highlight discrepancies between user expectations and the actual workings of social media algorithms. Users may feel they have more control over their content experience than is the case, potentially impacting their overall satisfaction with the platform.
✨ This summary was generated by AI from the outlets' reporting listed below. It is not independently verified and may contain errors — check the original sources. How BrevFeed works →
Northwestern University researchers found that TikTok's algorithm inadequately responds to negative user feedback. Despite users expressing disinterest, suggested videos often remain on their For You Page, limiting their perceived control over content curation.