Open AccessAnalysis of Indonesian Public Opinion Sentiment on Policy on Twitter Social Media “PPKM” Using K-Nearest Neighbor
Author(s) -
Aulia Khoirunnita,
Kusnawi Kusnawi
Publication year - 2021
Publication title -
tepian
Language(s) - English
Resource type - Journals
eISSN - 2721-5369
pISSN - 2721-5350
DOI - 10.51967/tepian.v2i4.508
Subject(s) - sentiment analysis , social media , computer science , the internet , indonesian , government (linguistics) , public opinion , preprocessor , data pre processing , process (computing) , k nearest neighbors algorithm , set (abstract data type) , artificial intelligence , information retrieval , political science , world wide web , philosophy , linguistics , politics , law , programming language , operating system
COVID-19 or Coronavirus disease 2019 is currently a pandemic that is spreading very quickly throughout the world, including Indonesia. Various handling and policies have been carried out, one of which is called “PPKM” policy or what can also be called the Enforcement of Restrictions on Community Activities issued by the Indonesian government. “PPKM” is currently one of the topics that is often discussed by the public, one of which is on the Twitter social media platform. The existence of opinions given by the community, it is necessary to have a sentiment analysis. Sentiment analysis is an analytical process obtained from various social media platforms and the internet. The aim is to find out how the public's sentiment towards the implementation of “PPKM” policies in Indonesia is through tweets and comments on the Twitter social media platform. In this study, the process of analyzing public opinion regarding the “PPKM” policy will be carried out by classifying opinions into 3 sentiments, namely positive, negative or neutral. Classification is done using the K-Nearest Neighbor algorithm. The K-Nearest Neighbor (K-NN) algorithm is a classification method for a set of data based on previously classified data learning. Included in supervised learning, where the results of the new query instance are classified based on the majority of the distance proximity of the categories in K-NN. The results of data preprocessing and sentiment classification, in the first test positive sentiment 37.6% of 261 data, negative sentiment 65.9% of 636 data and neutral sentiment 9.