Sentiment Analysis on Erspo Jersey in X Using Machine Learning Algorithms

Abstract

This research conducts a sentiment analysis on Erspo jerseys using machine learning algorithms on the X platform. The objective is to identify the public's sentiment and compare the performance of three algorithms: Naïve Bayes, K-Nearest Neighbor (KNN), and Support Vector Machine (SVM). Data was collected through web scraping of tweets between January and September 2024, containing keywords related to Erspo. Using a lexicon-based approach, the preprocessing steps involved cleaning, tokenizing, normalizing, and labeling data into positive, negative, and neutral sentiments. Results show that the Naïve Bayes algorithm provided the highest accuracy in sentiment classification, followed by SVM and KNN. Positive sentiment primarily centered on product loyalty, while negative sentiment largely criticized jersey design and quality. The findings offer important insights for Erspo stakeholders to refine marketing strategies and product improvements. This study highlights the potential of machine learning in analyzing consumer opinions at scale, making it a valuable tool for real-time consumer feedback analysis.