<![CDATA[The coronavirus outbreak that occurred in almost all countries in the world has had an impact not only on the health sector, but also on other sectors such as tourism, finance, transportation, etc. This has given rise to various kinds of sentiments from the public with the emergence of the coronavirus as a trending topic on social media Twitter. Twitter was chosen by the public because it can disseminate information in real time and can see the market's reaction quickly. In this study, "tweet" data or public tweets related to the "Coronavirus" were used to see how the polarity of sentiment emerged. Text mining techniques and K-Nearest Neighbour (K-NN) machine learning classification algorithms were used to build a tweet classification model on sentiment whether it has a positive, negative, or neutral polarity. The test results were produced by the algorithm with an average result for a precision value of 57.93% and for an average recall niali of 55.21% with an accuracy value of 64.52%]]>
Copyrights © 2024
