An Ensemble Classification of Mental Health in Malaysia related to the Covid-19 Pandemic using Social Media Sentiment Analysis

• Main Authors: Adli, Nur Aisyah Zakaria, Ahmad, Muneer, Ghani, Norjihan Abdul, Ravana, Sri Devi, Norman, Azah Anir
• Format: Article
• Published: Korean Society for Internet Information 2024
• Subjects: QA75 Electronic computers. Computer science
• Online Access: http://eprints.um.edu.my/45541/; https://doi.org/10.3837/tiis.2024.02.006
• Institution: Universiti Malaya

COVID-19 was declared a pandemic by the World Health Organization (WHO) on 30 January 2020. The lifestyle of people all over the world has changed since. In most cases, the pandemic has appeared to create severe mental disorders, anxieties, and depression among people. Mostly, the researchers have been conducting surveys to identify the impacts of the pandemic on the mental health of people. Despite the better quality, tailored, and more specific data that can be generated by surveys, social media offers great insights into revealing the impact of the pandemic on mental health. Since people feel connected on social media, thus, this study aims to get the people's sentiments about the pandemic related to mental issues. Word Cloud was used to visualize and identify the most frequent keywords related to COVID-19 and mental health disorders. This study employs Majority Voting Ensemble (MVE) classification and individual classifiers such as Naive Bayes (NB), Support Vector Machine (SVM), and Logistic Regression (LR) to classify the sentiment through tweets. The tweets were classified into either positive, neutral, or negative using the Valence Aware Dictionary or sEntiment Reasoner (VADER). Confusion matrix and classification reports bestow the precision, recall, and F1 -score in identifying the best algorithm for classifying the sentiments.