Article Per Year (5 Year)
p-Index From 2021 - 2026
0.23
P-Index
This Author published in this journals
All Journal Sistemasi: Jurnal Sistem Informasi
Petronilia Palinggik Allorerung
Universitas Dipa Makassar
Computer Science & IT Electrical & Electronics Engineering

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
Sentiment Analysis on WeTV App Reviews on Google Play Store Using NBC and SVM Algorithms Petronilia Palinggik Allorerung; Rismayani Rismayani
Sistemasi: Jurnal Sistem Informasi Vol 12, No 2 (2023): Sistemasi: Jurnal Sistem Informasi
Publisher : Program Studi Sistem Informasi Fakultas Teknik dan Ilmu Komputer

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32520/stmsi.v12i2.2518

Abstract

Since the Covid-19 outbreak hit Indonesia, all community activities have become very limited. The government's decision regarding PPKM to reduce the level of Covid-19 cases forced the community to reduce the level of activities outside the home including work. One activity that has recently been popular with the public is watching movies through the online streaming service available on the Google Play Store. Applications with high total downloads and ratings show people's interest in the application. The WeTV online streaming service is an application that has high downloads and ratings on the Google Play Store. This service provides various types of content from various countries. However, the WeTV application also has drawbacks that can be seen in the reviews from users. Based on this, research was conducted on the classification of positive and negative sentiments from WeTV application users. There are two classification algorithms implemented, namely Naïve Bayes Classifier (NBC) and Support Vector Machine (SVM). Apart from classifying positive and negative reviews, this sentiment analysis also aims to compare the performance of the two algorithms. The total data used is 100 data. After conducting sentiment analysis, it was concluded that the SVM classification method was the best classification method in this study with 80.00% accuracy, 80.00% precision, and 80.00% recall.
Co-Authors Rismayani Rismayani