Analisis Sentimen Masyarakat Terhadap Perkuliahan Daring di Twitter Menggunakan Algoritma Naive Bayes dan Support Vector Machine

Abstract

The COVID-19 pandemic has changed the education landscape around the world, resulting in the cessation of in-person teaching and learning activities and encouraging the adoption of online learning systems. Many Indonesians express their opinions and thoughts about online courses through the social media Twitter. Therefore, this study aims to analyze people's sentiment towards online lectures on Twitter using Naïve Bayes and Support Vector Machine (SVM) methods. Data for sentiment analysis is taken from Twitter using the keywords "#college", "#daring", and "#kuliahdaring". This study limits data collection to the range of 2021-2022. A total of 1,260 Tweets were analyzed, with 633 Tweets having positive sentiments and 627 Tweets having negative sentiments. This study uses Naïve Bayes and Support Vector Machine algorithms to classify positive and negative sentiments in Tweets. The results showed that Naïve Bayes algorithm achieved the highest accuracy of 72%, while Support Vector Machine achieved 66% accuracy.