Optimizing Prediction of YouTube Video Popularity Using XGBoost

Nisa, Meher Un; Mahmood, Danish; Ahmed, Ghufran; Khan, Suleman; Mohammed, Mazin Abed; Damaševičius, Robertas

doi:10.3390/electronics10232962

Cited by 16 publications

(3 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Jeon et al separated videos into different classes based on their popularity and release status [37] and trained classification models for both published and newly released videos with XGBoost and deep neural network classifiers, respectively. The classifier XGBoost was also successfully applied to the binary classification of YouTube video popularity after feature selection and fusion [38]. Sarkar et al introduced a deep neural network framework called ViViD to handle the multi-modal features and perform multiclass prediction for video popularity [39].…”

Section: Popularity Prediction Methodsmentioning

confidence: 99%

DanceTrend: An Integration Framework of Video-Based Body Action Recognition and Color Space Features for Dance Popularity Prediction

Ding,

Hou,

Liu

et al. 2023

Electronics

View full text Add to dashboard Cite

Background: With the rise of user-generated content (UGC) platforms, we are witnessing an unprecedented surge in data. Among various content types, dance videos have emerged as a potent medium for artistic and emotional expression in the Web 2.0 era. Such videos have increasingly become a significant means for users to captivate audiences and amplify their online influence. Given this, predicting the popularity of dance videos on UGC platforms has drawn significant attention. Methods: This study postulates that body movement features play a pivotal role in determining the future popularity of dance videos. To test this hypothesis, we design a robust prediction framework DanceTrend to integrate the body movement features with color space information for dance popularity prediction. We utilize the jazz dance videos from the comprehensive AIST++ street dance dataset and segment each dance routine video into individual movements. AlphaPose was chosen as the human posture detection algorithm to help us obtain human motion features from the videos. Then, the ST-GCN (Spatial Temporal Graph Convolutional Network) is harnessed to train the movement classification models. These pre-trained ST-GCN models are applied to extract body movement features from our curated Bilibili dance video dataset. Alongside these body movement features, we integrate color space attributes and user metadata for the final dance popularity prediction task. Results: The experimental results endorse our initial hypothesis that the body movement features significantly influence the future popularity of dance videos. A comprehensive evaluation of various feature fusion strategies and diverse classifiers discern that a pre–post fusion hybrid strategy coupled with the XGBoost classifier yields the most optimal outcomes for our dataset.

show abstract

Section: Popularity Prediction Methodsmentioning

confidence: 99%

DanceTrend: An Integration Framework of Video-Based Body Action Recognition and Color Space Features for Dance Popularity Prediction

Ding,

Hou,

Liu

et al. 2023

Electronics

View full text Add to dashboard Cite

show abstract

“…Spyder Python 3.8 is used for the implementation of this algorithm. To implement our proposed work for the data sets of Facebook, Twitter, 2023/1/52 and data sets, are available in Stanford University SNAP, Dolphin network, American college football network, karate club, YouTube data set [24]. Table 2 shows the information about the data set for the evaluation of metric measures.…”

Section: Data Setmentioning

confidence: 99%

Community Detection by Node Betweenness Using Optimized Girvan-Newman Cuckoo Search Algorithm

Devi¹,

Rajalakshmi²

2023

ITC

View full text Add to dashboard Cite

Due to technological development, social media platforms like forums and microblogs allow people to share their experiences, thoughts, and feelings. The organization, shopping groups etc. has major discussions regarding their business advertisements and product reviews. Also, there are certain followers for particular person or group due to their interests. Here the major issue is to know who or which group in social media is more influenced. The social media analysis needs to perform for identifying influenced person in the social media. The influencer node/person detection in a certain community is already done using greedy algorithm, genetic algorithm, ant colony optimization, cuckoo search algorithms. These existing techniques takes more time for diffusion and accuracy in prediction is not satisfied by users. To overcome this issues, in this research influencer node is identified using optimized Girvan Newman Cuckoo Search Algorithm (GNCSA). First Grivan Newman is used to identify the community and perform community detection. Cuckoo search algorithm uses host bird strategy in finding cuckoo eggs in his nest. Based on the centrality measure it decides whether the node is an influencer or not. This paper proposed Influencer detection by forming community first and measures angular centrality using optimized Girvan Newman cuckoo search algorithm. Our proposed work GNCSA gives a better accuracy rate for the data sets of Dolphin 0.89, for Facebook dataset got 0.93, Twitter data set got 0.94 and for YouTube data set 0.92, karate club and football got 0.91. This proposed work increases the intracommunity of the social network and improves its performance accurately by detecting the influencer in the social network.

show abstract

“…Many patients consult internet sources about their illness and treatment options [ 1 , 2 ]. YouTube is a digital sharing platform and the largest online video streaming source [ 3 , 4 ]. It is also the second most visited website with 5 billion daily views worldwide [ 5 ].…”

Section: Introductionmentioning

confidence: 99%

Radionuclide Therapy Videos on YouTube as An Educational Material: Has the COVID-19 Pandemic Changed the Quality, Usefulness, and Interaction Features

Korkmaz

Demir

Arda

2023

Nucl Med Mol Imaging

View full text Add to dashboard Cite

Introduction Current treatment approach aims to achieve greater efficacy with fewer side effects, by targeted cancer therapy as much as possible. Radionuclide therapy is a modality that uses cancer theranostics and is increasingly applied for various cancers as a targeted therapy. YouTube is a preferred tool for obtaining medical information from the internet. This study aims to determine the content quality, level of interaction and usefulness as education material of radionuclide therapy YouTube videos and to reveal the impact of the COVID-19 process on these parameters. Materials and MethodsThe keywords were searched on YouTube on August 25, 2018, and May 10, 2021. After removing duplicate and excluded videos, all remaining videos were scored and coded. Results Majority of the videos were useful educational material. Most of them were high quality. Popularity markers were unrelated to quality level. After COVID, the power index of videos with high JAMA scores increased. The COVID-19 pandemic did not have a negative effect on video features; the quality of the content increased even more after the pandemic. Conclusion Radionuclide therapy YouTube videos have high-quality content and provide useful education material. The popularity is independent of the content quality. During the pandemic, video quality and usefulness characteristics did not change, while the visibility is increased. We consider YouTube to be an appropriate educational material for patients and healthcare professionals to gain basic knowledge of radionuclide therapy. The Covıd-19 pandemic highlighted the power of radionuclide therapy YouTube videos as an educational material.

show abstract

Optimizing Prediction of YouTube Video Popularity Using XGBoost

Cited by 16 publications

References 40 publications

DanceTrend: An Integration Framework of Video-Based Body Action Recognition and Color Space Features for Dance Popularity Prediction

DanceTrend: An Integration Framework of Video-Based Body Action Recognition and Color Space Features for Dance Popularity Prediction

Community Detection by Node Betweenness Using Optimized Girvan-Newman Cuckoo Search Algorithm

Radionuclide Therapy Videos on YouTube as An Educational Material: Has the COVID-19 Pandemic Changed the Quality, Usefulness, and Interaction Features

Contact Info

Product

Resources

About