VIDEO POPULARITY PREDICTION USING STACKED BILSTM LAYERS

IF 1.1 4区计算机科学 Q4 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Malaysian Journal of Computer Science Pub Date : 2021-07-31 DOI:10.22452/mjcs.vol34no3.2

Neeti Sangwan, Vishal Bhatnagar

引用次数: 3

Abstract

Social media is now not only limited to being a life event sharing platform, but it also has evolved as a monetary medium. Advertisements showing on popular videos may result in more sales conversion. So it is of utmost interest to predict the popularity of videos before uploading it on the platform. In this research article, we propose a deep learning algorithm to predict the popularity of YouTube videos. With the content and temporal features of the YouTube videos dataset, we use a novel stack of deep learning layers. We validate the approach with state-of-the-art methods and prove that the proposed complex stacked architecture gives more accurate and stable results. Results are also tested for short duration prediction with a different number of reference days after video publishing.

查看原文本刊更多论文

使用堆叠BILSTM层预测视频流行度

社交媒体现在不仅局限于生活事件共享平台，而且已经发展成为一种货币媒介。流行视频上的广告可能会带来更多的销售转化。因此，在上传到平台上之前预测视频的受欢迎程度是最令人感兴趣的。在这篇研究文章中，我们提出了一种深度学习算法来预测YouTube视频的流行程度。根据YouTube视频数据集的内容和时间特征，我们使用了一个新颖的深度学习层堆栈。我们用最先进的方法验证了该方法，并证明了所提出的复杂堆叠结构提供了更准确和稳定的结果。还对视频发布后不同参考天数的短持续时间预测结果进行了测试。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Malaysian Journal of Computer Science COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE-COMPUTER SCIENCE, THEORY & METHODS

CiteScore

2.20

自引率

33.30%

发文量

审稿时长

7.5 months

期刊介绍： The Malaysian Journal of Computer Science (ISSN 0127-9084) is published four times a year in January, April, July and October by the Faculty of Computer Science and Information Technology, University of Malaya, since 1985. Over the years, the journal has gained popularity and the number of paper submissions has increased steadily. The rigorous reviews from the referees have helped in ensuring that the high standard of the journal is maintained. The objectives are to promote exchange of information and knowledge in research work, new inventions/developments of Computer Science and on the use of Information Technology towards the structuring of an information-rich society and to assist the academic staff from local and foreign universities, business and industrial sectors, government departments and academic institutions on publishing research results and studies in Computer Science and Information Technology through a scholarly publication. The journal is being indexed and abstracted by Clarivate Analytics'' Web of Science and Elsevier''s Scopus