When Youth Enter the Algorithmic Wild: Discovering and Understanding Potentially Harmful Teen Videos on Douyin and Kwai

• URL: http://arxiv.org/abs/2605.23598v1
• Date: Fri, 22 May 2026 13:06:46 GMT
• Title: When Youth Enter the Algorithmic Wild: Discovering and Understanding Potentially Harmful Teen Videos on Douyin and Kwai
• Abstract summary: Short-video platforms like Douyin and Kwai risk exposing teens to algorithmically amplified harmful content.<n>Despite its societal importance, the scale, mechanisms, and real-world impact of this exposure remain poorly understood.<n>We propose PHTV-Scout, the first large-scale, behaviorally grounded measurement framework for Potentially Harmful Teen Videos.
• Score: 6.933489114068085
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Short-video platforms like Douyin and Kwai have become central to adolescent digital life, but they also risk exposing teens to algorithmically amplified harmful content. Despite its societal importance, the scale, mechanisms, and real-world impact of this exposure remain poorly understood. Measuring it is challenging: recommendation feeds are personalized black boxes, harmful content employs sophisticated evasion tactics, and naive crawlers fail to replicate authentic teen behavior. To bridge this gap, we propose PHTV-Scout, the first large-scale, behaviorally grounded measurement framework for Potentially Harmful Teen Videos (PHTVs). We integrate an offline survey of 683 adolescents with a tri-module online pipeline: (1) PHTV Hunter simulates teen accounts to collect recommendation feeds; (2) PHTV Arbiter, a LoRA-finetuned multimodal classifier, detects PHTVs with 94.29% accuracy and 96.41% precision; and (3) PHTV Analyzer performs fine-grained categorization and impact assessment. Over six months, we analyzed 186,727 videos and 51,287 comments, uncovering a troubling 6.11% PHTV prevalence--dominated by Child Sexual Exploitation Imagery (53.2%)--and revealing that harmful content thrives through covert interactions (e.g., grooming comments, self-disclosure) and active evasion (semantic camouflage, noise injection). Crucially, while Youth Mode blocks 100% of PHTVs, its low adoption (30-41%) leaves most teens unprotected. We further show that exposure is driven not by user identity but by regulation, platform algorithms, and even passive browsing, exposing the fragility of adolescent information environments. Our findings call for a paradigm shift from reactive takedowns to proactive, human-centered safeguards.

Related papers

• Towards an Automated Framework to Audit Youth Safety on TikTok [6.83645418303131]
  This paper investigates the effectiveness of TikTok's enforcement mechanisms for limiting the exposure of harmful content to youth accounts.<n>We collect over 7000 videos, classify them as harmful vs not-harmful, and then simulate interactions using age-specific sockpuppet accounts.<n>Preliminary results show minimal differences in content exposure between adult and youth accounts, raising concerns about the platform's age-based moderation.
  arXiv  Detail & Related papers  (2025-09-06T21:30:11Z)
• Catching Dark Signals in Algorithms: Unveiling Audiovisual and Thematic Markers of Unsafe Content Recommended for Children and Teenagers [13.39320891153433]
  The prevalence of short form video platforms, combined with the ineffectiveness of age verification mechanisms, raises concerns about the potential harms facing children and teenagers in an algorithm-moderated online environment.<n>We conducted multimodal feature analysis and thematic topic modeling of 4,492 short videos recommended to children and teenagers on Instagram Reels, TikTok, and YouTube Shorts.<n>This feature-level and content-level analysis revealed that unsafe (i.e., problematic, mentally distressing) short videos possess darker visual features and contain explicitly harmful content and implicit harm from anxiety-inducing ordinary content.
  arXiv  Detail & Related papers  (2025-07-16T18:41:42Z)
• Adultification Bias in LLMs and Text-to-Image Models [55.02903075972816]
  We study bias along axes of race and gender in young girls.<n>We focus on "adultification bias," a phenomenon in which Black girls are presumed to be more defiant, sexually intimate, and culpable than their White peers.
  arXiv  Detail & Related papers  (2025-06-08T21:02:33Z)
• Protecting Young Users on Social Media: Evaluating the Effectiveness of Content Moderation and Legal Safeguards on Video Sharing Platforms [0.8198234257428011]
  We evaluated the effectiveness of video moderation for different age groups on TikTok, YouTube, and Instagram.<n>For passive scrolling, accounts assigned to the age 13 group encountered videos that were deemed harmful more frequently and quickly than those assigned to the age 18 group.<n>Exposure occurred without user-initiated searches, indicating weaknesses in the algorithmic filtering systems.
  arXiv  Detail & Related papers  (2025-05-16T12:06:42Z)
• Conspiracy theories and where to find them on TikTok [3.424635462664968]
  This study presents the first systematic analysis of conspiracy theories on TikTok.<n>We estimate a lower bound on the prevalence of conspiratorial videos.<n>We evaluate the capabilities of state-of-the-art open-weight Large Language Models to identify conspiracy theories.
  arXiv  Detail & Related papers  (2024-07-17T13:28:11Z)
• From Theft to Bomb-Making: The Ripple Effect of Unlearning in Defending Against Jailbreak Attacks [85.84979847888157]
  Large Language Models (LLMs) are known to be vulnerable to jailbreak attacks.<n>LLMs can implicitly unlearn harmful knowledge that was not explicitly introduced during the unlearning phase.<n>We empirically validate this phenomenon, which makes unlearning-based methods able to decrease the Attack Success Rate.
  arXiv  Detail & Related papers  (2024-07-03T07:14:05Z)
• Supporters and Skeptics: LLM-based Analysis of Engagement with Mental Health (Mis)Information Content on Video-sharing Platforms [19.510446994785667]
  One in five adults in the US lives with a mental illness. Short-form video content has grown to serve as a crucial conduit for disseminating mental health help and resources.
  arXiv  Detail & Related papers  (2024-07-02T20:51:06Z)
• Evaluating and Mitigating IP Infringement in Visual Generative AI [54.24196167576133]
  State-of-the-art visual generative models can generate content that bears a striking resemblance to characters protected by intellectual property rights. This happens when the input prompt contains the character's name or even just descriptive details about their characteristics. We develop a revised generation paradigm that can identify potentially infringing generated content and prevent IP infringement.
  arXiv  Detail & Related papers  (2024-06-07T06:14:18Z)
• Understanding writing style in social media with a supervised contrastively pre-trained transformer [57.48690310135374]
  Online Social Networks serve as fertile ground for harmful behavior, ranging from hate speech to the dissemination of disinformation. We introduce the Style Transformer for Authorship Representations (STAR), trained on a large corpus derived from public sources of 4.5 x 106 authored texts. Using a support base of 8 documents of 512 tokens, we can discern authors from sets of up to 1616 authors with at least 80% accuracy.
  arXiv  Detail & Related papers  (2023-10-17T09:01:17Z)
• An Image is Worth a Thousand Toxic Words: A Metamorphic Testing Framework for Content Moderation Software [64.367830425115]
  Social media platforms are being increasingly misused to spread toxic content, including hate speech, malicious advertising, and pornography. Despite tremendous efforts in developing and deploying content moderation methods, malicious users can evade moderation by embedding texts into images. We propose a metamorphic testing framework for content moderation software.
  arXiv  Detail & Related papers  (2023-08-18T20:33:06Z)
• Attacking Video Recognition Models with Bullet-Screen Comments [79.53159486470858]
  We introduce a novel adversarial attack, which attacks video recognition models with bullet-screen comment (BSC) attacks. BSCs can be regarded as a kind of meaningful patch, adding it to a clean video will not affect people' s understanding of the video content, nor will arouse people' s suspicion.
  arXiv  Detail & Related papers  (2021-10-29T08:55:50Z)
• Hate, Obscenity, and Insults: Measuring the Exposure of Children to Inappropriate Comments in YouTube [8.688428251722911]
  In this paper, we investigate the exposure of young users to inappropriate comments posted on YouTube videos targeting this demographic. We collected a large-scale dataset of approximately four million records and studied the presence of five age-inappropriate categories and the amount of exposure to each category. Using natural language processing and machine learning techniques, we constructed ensemble classifiers that achieved high accuracy in detecting inappropriate comments.
  arXiv  Detail & Related papers  (2021-03-03T20:15:22Z)
• Quantifying the Vulnerabilities of the Online Public Square to Adversarial Manipulation Tactics [43.98568073610101]
  We use a social media model to quantify the impacts of several adversarial manipulation tactics on the quality of content. We find that the presence of influential accounts, a hallmark of social media, exacerbates the vulnerabilities of online communities to manipulation. These insights suggest countermeasures that platforms could employ to increase the resilience of social media users to manipulation.
  arXiv  Detail & Related papers  (2019-07-13T21:12:08Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.