Half-life of Youtube News Videos: Diffusion Dynamics and Predictive Factors

2025-07-27

AI Summary

This study investigates early propagation dynamics and half-life prediction for YouTube news videos within the first 24 hours post-upload. Leveraging an original, large-scale dataset comprising over 50,000 news videos from 75 countries, we formally define and quantify a novel metric—“24-hour half-life”—revealing substantial cross-national heterogeneity (mean ≈ 7 hours; range: 2–15 hours). We propose a hybrid predictive framework integrating six statistical and deep learning models, augmented with eXplainable AI (XAI) techniques to interpret key drivers—including video content features and channel-level attributes. Our contributions are threefold: (1) the first large-scale, multi-national longitudinal dataset on YouTube news diffusion; (2) an interpretable, time-sensitive half-life prediction paradigm grounded in real-world propagation patterns; and (3) full open-sourcing of data, code, and models to ensure reproducibility and facilitate future research in digital news dissemination.

Technology Category

• Computer Vision: Interpretability, Explainability, and Transparency
• Machine Learning: Life-Long and Continual Learning
• Natural Language Processing: Interpretability, Analysis, and Evaluation of NLP Models

Application Category

• Web Mining and Content Analysis: Large pretrained models with web data
• Social Networks and Social Media: Influence propagation, information diffusion, and the prediction on networks
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web

Abstract

Consumption of YouTube news videos significantly shapes public opinion and political narratives. While prior works have studied the longitudinal dissemination dynamics of YouTube News videos across extended periods, limited attention has been paid to the short-term trends. In this paper, we investigate the early-stage diffusion patterns and dispersion rate of news videos on YouTube, focusing on the first 24 hours. To this end, we introduce and analyze a rich dataset of over 50,000 videos across 75 countries and six continents. We provide the first quantitative evaluation of the 24-hour half-life of YouTube news videos as well as identify their distinct diffusion patterns. According to the findings, the average 24-hour half-life is approximately 7 hours, with substantial variance both within and across countries, ranging from as short as 2 hours to as long as 15 hours. Additionally, we explore the problem of predicting the latency of news videos' 24-hour half-lives. Leveraging the presented datasets, we train and contrast the performance of 6 different models based on statistical as well as Deep Learning techniques. The difference in prediction results across the models is traced and analyzed. Lastly, we investigate the importance of video- and channel-related predictors through Explainable AI (XAI) techniques. The dataset, analysis codebase and the trained models are released at http://bit.ly/3ILvTLU to facilitate further research in this area.

Problem

• Analyzing short-term diffusion patterns of YouTube news videos
• Predicting 24-hour half-life latency using multiple models
• Identifying key factors influencing video half-life variance

Innovation

• Analyzes 24-hour diffusion patterns of YouTube news
• Uses statistical and Deep Learning models for prediction
• Applies Explainable AI to identify key predictors