Sentiment Analysis and Topic Classification of Twitter-based Data Set on the Face-to-face Classes Resumption in the Philippines during the COVID-19 Pandemic
Carlo R. Catayna, Maria Art Antonette D. Clariño · 2022
Due to the Corona Virus Disease 2019 (COVID-19) pandemic, there was a need for shift in pedagogy of education. Several delivery modes for educational materials and activities had to be implemented to adapt in the situation brought about by the pandemic. In the Philippines, there has been a call to fully transition to face-to-face classes expressed on social media. In this study, a data set was built consisting of tweets (Twitter data) regarding the resumption of face-to-face classes in the Philippines. This data set was subjected to training and testing to classify them in terms of topic and sentiment using Recurrent Neural Network Long Short-Term Memory (LSTM) and Multinomial Naïve Bayes. The LSTM sentiment classifier resulted to 78.33% accuracy and LSTM topic classifier produced 61.34% accuracy. The Multinomial Naïve Bayes classifier obtained 77.22% accuracy for classifying sentiment while 58.33% accuracy for topic classification.