Open AccessPerbandingan Algoritma Klasifikasi Sentimen Twitter Terhadap Insiden Kebocoran Data Tokopedia
Author(s) -
Nadhif Ikbar Wibowo,
Tri Andika Maulana,
Hamzah Muhammad,
Nur Aini Rakhmawati
Publication year - 2021
Publication title -
jiska (jurnal informatika sunan kalijaga)
Language(s) - English
Resource type - Journals
eISSN - 2528-0074
pISSN - 2527-5836
DOI - 10.14421/jiska.2021.6.2.120-129
Subject(s) - support vector machine , artificial intelligence , computer science , random forest , classifier (uml) , training set , logistic regression , data set , pattern recognition (psychology) , machine learning
Public responses, posted on Twitter reacting to the Tokopedia data leak incident, were used as a data set to compare the performance of three different classifiers, trained using supervised learning modeling, to classify sentiment on the text. All tweets were classified into either positive, negative, or neutral classes. This study compares the performance of Random Forest, Support-Vector Machine, and Logistic Regression classifier. Data was scraped automatically and used to evaluate several models; the SVM-based model has the highest f1-score 0.503583. SVM is the best performing classifier.