Classification of People’s Opinions on Fuel Subsidy Removal in Nigeria: An Enhancement of Unsupervised Learning Algorithm-Opinion Lexicon algorithm

This research aims tocollect Nigerians’ opinions on subsidy removal in Nigeria and classify them using an unsupervised learning algorithm, specifically corpus-based lexicon algorithm in order to enhance it prediction accuracy. The data was extracted from an online survey via social media platforms: Facebook and WhatsApp. A comprehensive literature review has been conducted on fuel subsidy removal, sentiment analysis, and unsupervised machine learning approach. The methodology involved are: data collection, preprocessing, feature extraction, model training, and evaluation. The result of this study shows that Nigerians are not happy with fuel subsidy removal, because of the highest numberof negative comments over positive ones. This implies that there exist in socio-economic and security issues in Nigeria. The unsupervised learning algorithm for sentiment analysis, the Lexicon was improved with an accuracy of 84.5%. thus,enhanced by 15.27%. These results can potentially inform policymakers and stakeholders about the public's sentiments, the social and security consequences of subsidy removal in Nigeria.