Multi-branch LSTM encoded latent features with CNN-LSTM for Youtube popularity prediction
Abstract 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...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-01-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-025-86785-3 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832585823825952768 |
|---|---|
| author | Neeti Sangwan Vishal Bhatnagar |
| author_facet | Neeti Sangwan Vishal Bhatnagar |
| author_sort | Neeti Sangwan |
| collection | DOAJ |
| description | Abstract 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 (R²) 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. |
| format | Article |
| id | doaj-art-0954c2178bcb4616becb64ba91cfa1d2 |
| institution | Kabale University |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-0954c2178bcb4616becb64ba91cfa1d22025-01-26T12:27:16ZengNature PortfolioScientific Reports2045-23222025-01-0115111510.1038/s41598-025-86785-3Multi-branch LSTM encoded latent features with CNN-LSTM for Youtube popularity predictionNeeti Sangwan0Vishal Bhatnagar1GGS Indraprastha University and Maharaja Surajmal Insitute of TechnologyNSUT East Campus (Formerly Ambedkar Institute of Advanced Communication Technologies and Research)Abstract 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 (R²) 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.https://doi.org/10.1038/s41598-025-86785-3PopularityPredictionRegressionDeep learning |
| spellingShingle | Neeti Sangwan Vishal Bhatnagar Multi-branch LSTM encoded latent features with CNN-LSTM for Youtube popularity prediction Scientific Reports Popularity Prediction Regression Deep learning |
| title | Multi-branch LSTM encoded latent features with CNN-LSTM for Youtube popularity prediction |
| title_full | Multi-branch LSTM encoded latent features with CNN-LSTM for Youtube popularity prediction |
| title_fullStr | Multi-branch LSTM encoded latent features with CNN-LSTM for Youtube popularity prediction |
| title_full_unstemmed | Multi-branch LSTM encoded latent features with CNN-LSTM for Youtube popularity prediction |
| title_short | Multi-branch LSTM encoded latent features with CNN-LSTM for Youtube popularity prediction |
| title_sort | multi branch lstm encoded latent features with cnn lstm for youtube popularity prediction |
| topic | Popularity Prediction Regression Deep learning |
| url | https://doi.org/10.1038/s41598-025-86785-3 |
| work_keys_str_mv | AT neetisangwan multibranchlstmencodedlatentfeatureswithcnnlstmforyoutubepopularityprediction AT vishalbhatnagar multibranchlstmencodedlatentfeatureswithcnnlstmforyoutubepopularityprediction |