Samantha Subaan, Carlina Amaba, Angie Canillo
In recent years, Twitter has gained popularity among social media users as a platform to express their thoughts and opinions. In the Philippines alone, more than 11 million users are actively using the real-time microblogging platform. With the knowledge of the 2022 Philippine election results, the researchers aim to predict the political preferences of Twitter users of that time. Using sentiment analysis, the researchers will determine a tweet’s polarity - determining whether it is positive, negative, or neutral. With the data, the model will then be created using three traditional machine learning algorithms: Naive Bayes, Support Vector Machine (SVM), and Logistic Regression. The listed algorithms will then be compared through cross-validation and accuracy metric testing in order to determine the most accurate algorithm between the three. A conclusion will be drawn, and results will be compared to the different types of algorithms and the actual 2022 Philippine Election results. © 2025 American Institute of Physics Inc.. All rights reserved.
University of San Carlos, Cebu City, Philippines
