Article Per Year (5 Year)
p-Index From 2020 - 2025
0.444
P-Index
This Author published in this journals
All Journal SMATIKA KLIK: Kajian Ilmiah Informatika dan Komputer
Allif Rizki Abdillah
Unknown Affiliation
Computer Science & IT Education

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

 1 
Analisis Sentimen Terhadap Kandidat Calon Presiden Berdasarkan Tweets Di Sosial Media Menggunakan Naive Bayes Classifier Allif Rizki Abdillah; Firman Noor Hasan
SMATIKA JURNAL : STIKI Informatika Jurnal Vol 13 No 01 (2023): SMATIKA Jurnal : STIKI Informatika Jurnal
Publisher : LPPM STIKI MALANG

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32664/smatika.v13i01.750

Abstract

This research is to analyze the sentiments of the Indonesian people about the presidential candidates who are likely to advance in the 2024 presidential election from tweets on the Twitter application. Tweets on Twitter are written, typed and published by Indonesian netizens about the candidates who are likely to advance in the 2024 presidential election. In this study, researchers used tools, namely RapidMiner Studio to collect tweet data from Indonesian netizens about the candidates. Furthermore, the researcher uses the Naïve Bayes Classifier algorithm to determine whether a statement or sentiment has a positive or negative value which is carried out using Rapid Miner tools as well. Of the four candidates that the researchers examined, Anies got 74% positive sentiment 26% negative sentiment, then followed by Sandi, namely 57% positive sentiment 43% negative sentiment, Ganjar received 53% positive sentiment 47% negative sentiment and Prabowo received 32% positive sentiment. 68% negative sentiment. The conclusion of this research is to find out which candidates are liked or favored by the Indonesian people from the results of sentiment analysis using the Naïve Bayes algorithm and the tools used, namely Rapid Miner.
Analisis Sentimen Ulasan Pengguna Aplikasi Netflix Pada Google Play Menggunakan Algoritma Naïve Bayes Ananda Bagas Pranata; Allif Rizki Abdillah; Faldy Irwiensyah
KLIK: Kajian Ilmiah Informatika dan Komputer Vol. 4 No. 6 (2024): Juni 2024
Publisher : STMIK Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/klik.v4i6.1964

Abstract

The rapid development of information technology has advanced rapidly, including advancements in film technology. In this modern era, watching movies no longer requires going to the cinema, as there are applications available to watch movies anytime and anywhere. One popular application for watching movies is Netflix, a widely used streaming platform for films and series. Netflix also ranks 10th in terms of access in Indonesia. This study focuses on identifying user satisfaction levels with the Netflix application based on reviews on the Google Play Store. The research aims to analyze user review sentiment of an application available on Google Play, namely Netflix. These reviews will be used to gauge user satisfaction with the Netflix application. Researchers obtained these reviews using a Python web scraper with a total of 1000 unprocessed data points. After processing these 1000 data points by removing duplicates and symbols, researchers obtained 893 data points ready for sentiment analysis using RapidMiner. Out of the 893 data points, researchers manually labeled 635 data points, while 258 data points were labeled automatically using machine learning, namely Naive Bayes. Researchers also created a confusion matrix to determine the accuracy level of the algorithm used in this study. The accuracy result of the confusion matrix obtained by researchers in this study is 93.39%. The positive class precision value of 85.52% indicates that most positive reviews were identified accurately, while the negative class precision value of 100% demonstrates excellent capability in identifying negative reviews. In conclusion, the Netflix application receives diverse responses from users, and the algorithm used effectively identifies reviews accurately
Co-Authors Ananda Bagas Pranata Faldy Irwiensyah Firman Noor Hasan