TikTok’s For You Page (FYP) may not offer users as much control as they believe, according to a study conducted by Northeastern University computer scientists. The research, published in a recent paper, highlights how TikTok's algorithm primarily relies on implicit and explicit engagement signals to curate content for users.
User Feedback and TikTok's Algorithm
The study reveals that while user engagement, such as likes and follows, influences the algorithm, negative feedback does not have a lasting impact. Users have reported that even after selecting the 'not interested' option for certain videos, these unwanted posts continue to appear on their FYP.
According to co-author Piotr Sapiezynski, the engagement signals affect content visibility temporarily. “When you start saying, ‘I don’t want to see this particular topic,’ the platform might actually show you fewer of such pieces of content. But then the platform will slowly start putting it back in your feed,” he explained.
Research Methodology and Findings
The researchers employed a unique methodology by creating bot accounts on TikTok to analyze how the algorithm responds to various engagement signals. They focused their experiments on three popular topics: cooking, fitness, and sports betting.
