Evaluating Uber Customers' Perception Through Machine Learning Techniques: A Case Study in Ecuador

This study analyzes the perception of Uber users through Twitter, currently known as X, using the CRISP-DM methodology in Python. We collected data from the last twelve years to accomplish this study. The data set is divided into training and testing, processing them using natural language processing and classifying them as neutral, positive, and hostile. Classification algorithms such as Logistic Regression, Support Vector Machines (SVM), and Naive Bayes are applied, with SVM being the most effective in predicting user sentiments. This approach leverages Twitter accessibility and data analytics to understand the public perception of Uber.