POPULARITY PREDICTION OF SHORT VIDEOS USING INTERNET OF THINGS AND NEURAL NETWORKS
Keywords:
Popularity Prediction, Short Videos, Internet of Things (IoT), Neural Networks, Deep Learning, User Engagement, Video Analytics, Social Media, Recurrent Neural Networks (RNN), Convolutional Neural Networks (CNN), Predictive Modeling, Viral Content Detection.Abstract
This research focuses on the popularity prediction of short videos by leveraging the capabilities of the Internet of Things (IoT) and Neural Networks. With the rapid rise of short video platforms such as TikTok, Instagram Reels, and YouTube Shorts, understanding and predicting what content becomes viral has become a valuable challenge. The Internet of Things enables real-time data collection from various user interactions and environmental contexts, including view counts, likes, shares, location, device type, and viewing time. This data is processed and analyzed using advanced neural network architectures, such as Convolutional Neural Networks (CNNs) for visual content analysis and Recurrent Neural Networks (RNNs) for temporal behavior prediction. The proposed model integrates these data streams to forecast the potential popularity of a video shortly after upload. Experimental results on benchmark short video datasets show significant improvement in prediction accuracy compared to traditional machine learning methods. The findings of this study can assist content creators, marketers, and platform developers in optimizing content strategies and enhancing user engagement.
