Short-Form Video Viewing Behavior Analysis and Multi-Step Viewing Time Prediction

TL;DR

This paper analyzes user viewing behavior in short-form videos to improve chunk-based preloading, demonstrating that Auto-ARIMA effectively predicts viewing times and reduces data wastage.

Contribution

It constructs a user behavior dataset for short videos and evaluates forecasting algorithms, highlighting Auto-ARIMA's superior performance for preloading optimization.

Findings

Auto-ARIMA achieves the lowest forecasting errors

Standard algorithms vary in stability and accuracy

Dataset is publicly available for further research

Abstract

Short-form videos have become one of the most popular user-generated content formats nowadays. Popular short-video platforms use a simple streaming approach that preloads one or more videos in the recommendation list in advance. However, this approach results in significant data wastage, as a large portion of the downloaded video data is not used due to the user's early skip behavior. To address this problem, the chunk-based preloading approach has been proposed, where videos are divided into chunks, and preloading is performed in a chunk-based manner to reduce data wastage. To optimize chunk-based preloading, it is important to understand the user's viewing behavior in short-form video streaming. In this paper, we conduct a measurement study to construct a user behavior dataset that contains users' viewing times of one hundred short videos of various categories. Using the dataset, we evaluate the performance of standard time-series forecasting algorithms for predicting user viewing time in short-form video streaming. Our evaluation results show that Auto-ARIMA generally achieves the lowest and most stable forecasting errors across most experimental settings. The remaining methods, including AR, LR, SVR, and DTR, tend to produce higher errors and exhibit lower stability in many cases. The dataset is made publicly available at https://nvduc.github.io/shortvideodataset.