"They've Over-Emphasized That One Search": Controlling Unwanted Content on TikTok's For You Page

TL;DR

The paper examines how TikTok users perceive and contend with unwanted content on the For You Page, introducing the notion of algorithmic persistence as the algorithm's apparent resistance to user resistance. Through 14 semi-structured interviews and a grounded-theory analysis, the authors map folk theories about how the FYP works and document tactical strategies users employ, including scrolling away, keyword filtering, and positive reinforcement. They define algorithmic persistence as the sustained delivery of undesired content despite user actions and discuss its implications for algorithmic literacy and platform design, as well as the erosion of the platform spirit. The study offers concrete insights into how users navigate content bubbles, with implications for researchers and practitioners aiming to improve user control over recommender systems and to explore persistence-aware approaches to user education. Limitations include sample size and time-bound observations, suggesting replication and extension to other platforms and evolving algorithms.

Abstract

Modern algorithmic recommendation systems seek to engage users through behavioral content-interest matching. While many platforms recommend content based on engagement metrics, others like TikTok deliver interest-based content, resulting in recommendations perceived to be hyper-personalized compared to other platforms. TikTok's robust recommendation engine has led some users to suspect that the algorithm knows users "better than they know themselves," but this is not always true. In this paper, we explore TikTok users' perceptions of recommended content on their For You Page (FYP), specifically calling attention to unwanted recommendations. Through qualitative interviews of 14 current and former TikTok users, we find themes of frustration with recommended content, attempts to rid themselves of unwanted content, and various degrees of success in eschewing such content. We discuss implications in the larger context of folk theorization and contribute concrete tactical and behavioral examples of algorithmic persistence.