Open AccessAnalisa Tanggapan Terhadap Psbb Di Indonesia Dengan Algoritma Decision Tree Pada Twitter
Author(s) -
Aditya Quantano Surbakti,
Regiolina Hayami,
Januar Al Amien
Publication year - 2021
Publication title -
jurnal computer science and information technology
Language(s) - English
Resource type - Journals
eISSN - 2723-567X
pISSN - 2723-5661
DOI - 10.37859/coscitech.v2i2.2851
Subject(s) - decision tree , naive bayes classifier , social media , computer science , preprocessor , sentiment analysis , classifier (uml) , precision and recall , data pre processing , artificial intelligence , data mining , world wide web , support vector machine
Community opinions are sometimes difficult to convey to the person in charge directly, it encourages people to express their opinions, criticisms and the like through social media, one of which is the popular social media today is Twitter. One collection of opinions or tweets from Twitter users about the PSBB effect one of which can be used as an analysis of public opinion sentiments. Data on the effects of PSBB were obtained as many as 2439 tweets, then processed using data mining techniques (data mining), in which there are processes of Collecting Data, text preprocessing and classification. Then it is tested into three different algorithms to be compared, the algorithm used is Decision Tree, Naïve Bayes Classifier and K-Nearest Neighbors (K-NN ) with the aim of finding the best accuracy. The highest results from this study were the Decision Tree algorithm with an accuracy value of 84.78%, precision 84.78% and recall 100%.
Keywords: twitter, sentiment analysis, decision tree