Honey Badger Algorithm with Voting Ensemble Based Computational Linguistics Enabled YouTube Video Popularity Prediction

Computational linguistics dealing with or designing models for language for precise machine translation of language or looking at the ways that machine treats natural language, or the simulation of artificial intelligence. YouTube is an income source for several people, and so video's popularity eventually develops the high importance to sustaining a stable income, offered that the eminence of videos remains at the maximum. Researchers and analysts utilize distinct approaches and techniques for predicting the maximal viewers of famous videos. The significance of identifying the celebrity of online videos and predicting the achievement of videos or conversely is an undeniable detail. Researchers and analysts utilize distinct techniques and models for predicting the maximal viewers of famous videos. In this aspect, a new Honey Badger Algorithm with Voting Ensemble based Machine Learning (HBA-VEML) model for YouTube Video Popularity Prediction is proposed in this study. The goal of the presented HBA-VEML technique is the prediction of YouTube video popularity accurately and promptly. It encompasses a series of processes such as pre-processing, feature extraction, prediction, and parameter optimization. Initially, the HBA-VEML technique undergoes data pre-processing and feature extraction. Next, a voting ensemble classifier is derived using three machine learning (ML) models such as logistic regression (LR), Naïve Bayes (NB), and support vector machine (SVM). To enhance the classification outcomes, the HBA is utilized as parameter optimizer. The performance validation of HBA-VEML technique is assessed on YouTube dataset. An extensive set of comparison results demonstrate the enhanced outcomes of the HBA-VEML method over other recent approaches.