Ensemble-Based Techniques: A review on Sentiment Analysis in Social Network with Boosting Techniques
Nisha Bali, Kulvinder Singh, Sanjeev Dhawan · 2023
Sentiment Analysis (SA) falls under the domain of Natural Language Processing (NLP), often known as opinion mining. Its objective is to identify and comprehensively analyze sentiments conveyed in comments. It is commonly recognized that the internet and online social media platforms present significant opportunities for this particular area. The main aim of this paper is to examine the obstacles related to $S A$, along with the most efficient algorithms for automated SA. As a component of our research, we have examined the effectiveness of ensemble techniques utilizing bagging and boosting methodologies for social networks. In addition, we have thoroughly examined the diverse tiers of Sentiment Analysis, along with its practical implementations, and the complexities associated with analyzing different domains utilizing machine algorithms such as Naïve-Bayes (NB), RandomForest (RF), Support Vector Machine (SVM), and K-NearestNeighbor (KNN). These algorithms have been extensively deliberated in numerous scholarly articles, shedding light on their merits and limitations. To conduct a comprehensive review, we have carefully chosen studies published between 2016 and 2023 from esteemed sources such as ACM, Science Direct, Scopus, and IEEE. The purpose of this paper is to present a meticulous analysis of $S A$ in social networks and to provide valuable benchmark information that can serve as a guide for future research endeavors.