Article Per Year (5 Year)
p-Index From 2020 - 2025
0.23
P-Index
This Author published in this journals
All Journal Jurnal Teknologi Informasi, Komputer, dan Aplikasinya (JTIKA )
Irawansyah, Rody Safri
Unknown Affiliation
Computer Science & IT Decision Sciences, Operations Research & Management Engineering

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

Found 1 Documents
Search

 1 
ANALISIS SENTIMEN TERHADAP PROGRAM MERDEKA BELAJAR-KAMPUS MERDEKA (MBKM) PADA TWITTER MENGGUNAKAN ALGORITMA NAIVE BAYES CLASSIFIER Irawansyah, Rody Safri; Irfan A, Lalu A. Syamsul; Wiriasto, Giri Wahyu
JTIKA (Jurnal Teknik Informatika, Komputer dan Aplikasinya) Vol 5 No 2 (2023): September 2023
Publisher : Program Studi Teknik Informatika, Fakultas Teknik, Universitas Mataram

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29303/jtika.v5i2.283

Abstract

Merdeka Belajar-Kampus Merdeka (MBKM) is a policy of the Indonesian Ministry of Education and Culture, which plays an important role in autonomous and flexible learning in student learning activities outside of study programs. However, MBKM has pros and cons, so it is necessary to analyze and evaluate its policies to improve performance through feedback from the community. This research will conduct a sentiment analysis on the MBKM policy on Twitter user tweets from 2022 with the keywords "MBKM", "kampus merdeka" and "merdekbelajar". The Naive Bayes Classifier (NBC) is used to analyze multiclass sentiment in Indonesian tweets into 3 (Three) Sentiment classes. Dataset collection and preparation begins with feature selection, eliminating duplication and tweet selection, then pre-processing is carried out, namely case folding, tokenizing, character cleaning, normalization to stemming for use in Labeling using Textblob which is required in making the Naïve Bayes Classifier model. The results of this study resulted in the Naïve Bayes model which had been trained from training data of 300 tweets with the best accuracy value of 79.66% having a Precision value of 79%, a Recall value of 80% and an F1-Score value of 79%. from the test of 1175 data the results were dominated by positive sentiment, namely 53.44%, followed by "neutral" sentiment, namely 34.47%, and "negative" sentiment, namely 12.08%.
Co-Authors Giri Wahyu Wiriasto Irfan A, Lalu A. Syamsul