Twitter is one of the social media that functions to express opinions on issues or problems that are currently happening, such as problems in the social, economic, educational and other fields. One of the issues being discussed so far is online learning. The government has issued a policy, one of which is for all students to study at home online by using a network to be able to interact with each other like in the classroom. The government's reason for issuing this policy is to break the chain of the spread of the Covid-19 virus, which until now has not subsided. Regarding this online learning policy, there are pros and cons. This opinion is widely expressed on social media, one of which is Twitter. Sentiment analysis is a method for analyzing an opinion which aims to classify texts. The Naïve Bayes Classifier and Support Vector Machine methods are methods machine learning that can be used for sentiment analysis. The problem in classifying text is that the resulting accuracy is less than optimal, so feature selection or boosting is needed to improve its accuracy. In this study, optimization of boosting was carried out using Adaboost. The purpose of this study is to compare the performance of the algorithm before and after using Adaboost. The results of the sentiment analysis on online learning obtained the highest accuracy results by the Naïve Bayes Classifier algorithm coupled with Adaboost of 99.26%, with a precision of 99.39% and recall of 99.20%.
Copyrights © 2023