Article Per Year (5 Year)
p-Index From 2020 - 2025
0.23
P-Index
This Author published in this journals
All Journal Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer
Reza Aprilliana Fauzi
Fakultas Ilmu Komputer, Universitas Brawijaya
Computer Science & IT Control & Systems Engineering Education Electrical & Electronics Engineering Engineering

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

Found 1 Documents
Search

 1 
Pemanfaatan Spark untuk Analisis Sentimen Mengenai Netralitas Berita dalam Membahas Pemilu Presiden 2019 Menggunakan Metode Naive Bayes Classifier: Utilization of Spark for Sentiment Analysis Regarding News Neutrality for Discussing the 2019 Presidential Election Using the Naive Bayes Classifier Method Reza Aprilliana Fauzi; Imam Cholissodin; Bayu Rahayudi
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 5 No 3 (2021): Maret 2021
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

An actual and neutral news is the hope of the public as the recipient of information to the news delivery media. Especially during the General Election in Indonesia, there are still news that are conveyed in a one side or not actual way. This also makes people still view that a lot of news has an element of partiality in providing information. Therefore, this study analyzes news sentiment from various news portals that discuss the 2019 Election in Indonesia. The data in this study were taken from various news portals and each news portal took 20 to 25 news stories, resulting in a large amount of data up to 100 data. This study using the Resilient Distributed Dataset (RDD) from the Spark platform as a data type in classifying news sentiments. The method used to classify the sentiment of a data (in this case is a news text) is the Naive Bayes Classifier method. Naive Bayes method has a good ability in classifying an unstructured big data, and has a simple model. This study uses the Confusion Matrix table as an evaluation table of the results of news sentiment classification, by calculating evaluation values such as accuracy, precision, recall, and F-Measure. Based on the various tests and scenarios that have been carried out, the best evaluation value is generated in the test using K-Fold Cross Validation with a value of K=10. In the 8th fraction (fold), the accuracy value is 100%, precision is 100%, recall is 100%. , and F-Measure of 100%.
Co-Authors Bayu Rahayudi Imam Cholissodin