Klasifikasi Tweet di Twitter dengan Menggunakan Metode K-Nearest Neighbor

Abstract

Twitter is a social media and also a microblog that allows users to send and read short messages of no more than 280 characters as tweets. Tweet users are currently not limited in terms of age, information, and communication. The lack of information on tweets on Twitter results in a lot of information that is difficult to know the facts or intentions of the tweet. This can have negative impacts such as fraud, leading public opinion to negative. One of the topics that has been discussed in Indonesian society since March 2020. Coranavirus Disease 2019 (COVID-19) is a disease of the new type of coronavirus virus (SARS-CoV-2) that has taken the world by storm and the WHO has declared it a pandemic. As of March 10, 2022, 5.85 million Covid cases have been confirmed out of a total of 453 million cases in the world. This Covid-19 case can be a place for certain parties to disseminate information to the wider community. Tweet data obtained from social networks based on queries in Indonesian, this study aims to determine the pros or cons of the public or society against Covid-19. To find out that a tweet is counter can be done by looking at the existing tweets one by one, but this takes a long time and effort because of the large number of tweets. In this study using the K-Nearest Neighbor (KNN) method using as many as 1200 tweet data. Based on the research that has been done, it can be said that public sentiment in 2020 regarding COVID-19 tends to be negative, followed by positive and neutral opinions. But in 2021, as time goes by, public opinion tends to follow neutral.