Publications

Investigation on the Self-Improving Algorithm of TikTok Based on Extensive User Interactions

Xiaoxing Chen
Department of Computer Science and Engineering, The Ohio State University

Conference / Publisher:
SCITEPRESS, 2024

Abstract:
This paper investigates TikTok’s self-improving recommendation algorithm and its ability to curate personalized content through extensive user interactions. Using survey-based analysis across university populations, the study highlights the role of metadata tags and autonomous learning mechanisms. The work discusses how advanced machine learning techniques—including Graph Neural Networks (GNN), Reinforcement Learning (RL), Temporal Convolutional Networks (TCN), Natural Language Processing (NLP), Generative Adversarial Networks (GANs), and attention mechanisms—contribute to progressive refinement of recommendations, improved user engagement, and enhanced content relevance.

Keywords:
TikTok, Recommendation Systems, Social Media, User Interaction, Machine Learning

Paper:
PDF – SCITEPRESS