Article Per Year (5 Year)
p-Index From 2019 - 2024
1.733
P-Index
This Author published in this journals
All Journal Jurnal Teknologi Informasi dan Ilmu Komputer JURNAL MEDIA INFORMATIKA BUDIDARMA JURIKOM (Jurnal Riset Komputer) Jurnal Mantik
Abdul Fadlil
Universitas Ahmad Dahlan, Yogyakarta
Computer Science & IT Control & Systems Engineering Economics, Econometrics & Finance Electrical & Electronics Engineering Engineering Languange, Linguistic, Communication & Media

Published : 11 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 11 Documents
Search

 1   2 
Analisis Sentimen HateSpeech pada Pengguna Layanan Twitter dengan Metode Naïve Bayes Classifier (NBC) Murni Murni; Imam Riadi; Abdul Fadlil
JURIKOM (Jurnal Riset Komputer) Vol 10, No 2 (2023): April 2023
Publisher : STMIK Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/jurikom.v10i2.5984

Abstract

In January 2023, Twitter users experienced a significant increase of 27.4% compared to the previous year. The social media platform Twitter is commonly used to share various types of information. One type of information frequently shared by users is Hate Speech. Hate Speech involves the dissemination of messages that nurture feelings of hatred and hostility towards specific individuals or groups, including ethnicity, religion, race, and other categories. Forms of Hate Speech encompass insults, defamation, blasphemy, provocation, incitement, and the spread of fake news. In order to address the potential for division and threats to Indonesia's unity, sentiment analysis capable of categorizing tweets as Hate Speech or Non-Hate Speech is necessary. This research aims to conduct sentiment analysis on Hate Speech tweets posted by Twitter users using the Naïve Bayes Classifier method. The dataset consists of 5000 samples processed using the Python programming language. Data processing stages involve preprocessing (including case folding, tokenization, stopword removal, normalization, and stemming), labeling, and assigning word weights (Term Weighting) using the Term Frequency (TF) and Inverse Document Frequency (IDF) methods. The data is then divided into training and testing sets, with three different data splits: 70% training and 30% testing, 30% training and 70% testing, and 50% training and 50% testing. Evaluation using the Confusion Matrix yields the highest accuracy of 81%, precision of 81%, recall of 100%, and F1-Score of 90% in the 70% training and 30% testing data split.
Co-Authors Amirul Mumin Bambang Subana Dikky Praseptian M Fitrah Juliansyah Herman Herman Ibnu Muakhori Imam Riadi Murni Murni Musri Iskandar Nasution Nur Makkie Perdana Kusuma Rezki Ramdhani Rusydi Umar Sunardi, Sunardi Yuniarti Lestari