Abstract :

The Rapid Growth Of Short Video Platforms Has Created A Need For Intelligent Systems That Can Accurately Estimate The Popularity Of Newly Published Content. Early Prediction Of Video Performance Helps Content Creators Improve Their Strategies, While Enabling Social Media Platforms To Deliver More Relevant Recommendations To Users. This Study Presents A Hybrid Deep Learning Framework For Intelligent Short Video Popularity Prediction That Combines Deep Learning With Intelligent Data Analytics To Forecast The Popularity Of Short Videos Immediately After Publication. The Proposed Framework Analyses Publisher-related Information Together With Textual And Contentbased Features To Identify Factors That Influence User Engagement. Data Preprocessing And Feature Extraction Are Performed Before Training The Hybrid Deep Learning Model To Improve Prediction Accuracy And Reduce Unnecessary Noise. The Developed Model Is Evaluated Using Standard Performance Metrics, Including Accuracy, Mean Squared Error (MSE), Mean Absolute Error (MAE), And Cross-entropy Loss. Experimental Results Demonstrate That The Proposed Framework Achieves Higher Prediction Accuracy And Lower Error Rates Than Conventional Prediction Models. The Developed System Provides An Effective Decision Support Tool For Content Creators And Social Media Platforms, Enabling Improved Content Recommendation, Audience Engagement, And Intelligent Popularity Forecasting.

Published:

30-7-2026

Issue:

Vol. 26 No. 7 (2026)

Page Nos:

1380-1385

Section:

Articles

License:

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

How to Cite