Multi-branch LSTM encoded latent features with CNN-LSTM for Youtube popularity prediction

被引:0
作者
Sangwan, Neeti [1 ,2 ]
Bhatnagar, Vishal [3 ]
机构
[1] GGS Indraprastha Univ, New Delhi, India
[2] Maharaja Surajmal Insitute Technol, New Delhi, India
[3] Ambedkar Inst Adv Commun Technol & Res, NSUT East Campus, New Delhi, India
来源
SCIENTIFIC REPORTS | 2025年 / 15卷 / 01期
关键词
Popularity; Prediction; Regression; Deep learning; VIDEOS; MODEL;
D O I
10.1038/s41598-025-86785-3
中图分类号
O [数理科学和化学]; P [天文学、地球科学]; Q [生物科学]; N [自然科学总论];
学科分类号
07 ; 0710 ; 09 ;
摘要
As digital media grows, there is an increasing demand for engaging content that can captivate audiences. Along with that, the monetary conversion of those engaging videos is also increased. This leads to the way for more content-driven videos, which can generate revenue. YouTube is the most popular platform which shared the revenue from advertisement to video publisher. This paper focuses on the work of video popularity prediction of the YouTube data. The idea of mapping the video features into low-dimensional space to get the latent features is presented. This mapping is achieved by a novel multi-branch child-parent Long Short Term Memory (LSTM) network. These latent features train the fused Convolutional Neural Network (CNN) with LSTM to predict the popularity of unseen videos on the trained deep learning network. We compared our results against Linear Regression (LR), Support Vector Regression (SVR) and Fully Convolutional Networks (FCN) with LSTM. A significant improvement with a 50% reduction in MAE and a 0.61% increase in the coefficient of determination (R-2) has been observed by the proposed Multi branch LSTM encoded features with a fused deep learning predictor (MLEF-DL predictor) when compared to existing methods.
引用
收藏
页数:15
相关论文
共 50 条
[31]   Short-term power load prediction based on CNN-LSTM model [J].
Chen, Jiawen ;
Cai, Chao ;
Yan, Fangbin ;
Liu, Jinfeng .
INTERNATIONAL JOURNAL OF COMPUTING SCIENCE AND MATHEMATICS, 2025, 21 (01) :77-89
[32]   Advanced thermal prediction for green roofs: CNN-LSTM model with SSA optimization [J].
Wang, Jun ;
Xu, Ding ;
Yang, Wansheng ;
Lai, Ling ;
Li, Feng .
ENERGY AND BUILDINGS, 2024, 322
[33]   An Attention-Based CNN-LSTM Method for Effluent Wastewater Quality Prediction [J].
Li, Yue ;
Kong, Bin ;
Yu, Weiwei ;
Zhu, Xingliang .
APPLIED SCIENCES-BASEL, 2023, 13 (12)
[34]   Parkinson Disease Prediction Using CNN-LSTM Model from Voice Signal [J].
Pandey P.V.K. ;
Sahu S.S. ;
Karan B. ;
Mishra S.K. .
SN Computer Science, 5 (4)
[35]   Medical-Based Text Classification Using FastText Features and CNN-LSTM Model [J].
Zeghdaoui, Mohamed Walid ;
Boussaid, Omar ;
Bentayeb, Fadila ;
Joly, Frederik .
DATABASE AND EXPERT SYSTEMS APPLICATIONS, DEXA 2021, PT I, 2021, 12923 :155-167
[36]   Continuous Intention Prediction of Lifting Motions Using EMG-Based CNN-LSTM [J].
Gwon, Min-Seong ;
Woo, Jong-Ha ;
Sahithi, Karur Krishna ;
Kim, Sang-Ho .
IEEE ACCESS, 2024, 12 :42453-42464
[37]   Prediction Sentiment Polarity using Past Textual Content and CNN-LSTM Neural Networks [J].
Belhareth, Yassin ;
Latiri, Chiraz .
PROCEEDINGS OF THE 17TH INTERNATIONAL CONFERENCE ON WEB INFORMATION SYSTEMS AND TECHNOLOGIES (WEBIST), 2021, :242-249
[38]   Prediction of irrigation water requirement based on parallel CNN-LSTM model and Mann-Kendall test [J].
Wen, Hao ;
Ma, Haochen ;
Du, Yu ;
Zhang, Jinchao ;
He, Li .
2024 IEEE 7TH INTERNATIONAL CONFERENCE ON INDUSTRIAL CYBER-PHYSICAL SYSTEMS, ICPS 2024, 2024,
[39]   A Novel Hybrid CNN-LSTM Scheme for Nitrogen Oxide Emission Prediction in FCC Unit [J].
He, Wei ;
Li, Jufeng ;
Tang, Zhihe ;
Wu, Beng ;
Luan, Hui ;
Chen, Chong ;
Liang, Huaqing .
MATHEMATICAL PROBLEMS IN ENGINEERING, 2020, 2020
[40]   A CNN-LSTM Model Trained with Grey Wolf Optimizer for Prediction of Household Power Consumption [J].
Gottam, Shilpa ;
Nanda, Satyasai Jagannath ;
Maddila, Ravi Kumar .
2021 IEEE INTERNATIONAL SYMPOSIUM ON SMART ELECTRONIC SYSTEMS (ISES 2021), 2021, :355-360