Article Per Year (5 Year)
p-Index From 2021 - 2026
0.444
P-Index
This Author published in this journals
All Journal JUITA : Jurnal Informatika Anglophile Journal
Deshinta Arrova Dewi
INTI International University, Malaysia
Computer Science & IT Education Languange, Linguistic, Communication & Media

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

Found 2 Documents
Search

 1 
Performance Analysis of Resampling Techniques for Overcoming Data Imbalance in Multiclass Classification Anggit Larasati; Sugiyarto Surono; Aris Thobirin; Deshinta Arrova Dewi
JUITA: Jurnal Informatika JUITA Vol. 13 Issue 1, March 2025
Publisher : Department of Informatics Engineering, Universitas Muhammadiyah Purwokerto

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30595/juita.v13i1.25270

Abstract

In the digital era, the development of modern technology has brought significant transformation to the medical world. The main objective of this research is to identify the performance of deep learning models in classifying kidney disease. By integrating the Convolutional Neural Network model, the performance of the classification process can be analyzed effectively and efficiently. However, data imbalance dramatically affects the performance evaluation of a model, requiring data resampling techniques. This research applies two resampling techniques, bootstrap-based random oversampling and random undersampling, to training data and adds data augmentation to increase image variations to prevent model overfitting. The architecture uses MobileNetV2, which compares hyperparameter fine-tuning in three optimizers. This research shows that the performance of MobileNetV2, which implements the bootstrap-based random oversampling technique, has the highest accuracy compared to random undersampling and no resampling methods. The oversampling technique with the RMSprop optimizer produced the highest accuracy, namely 95%. With precision, recall, and F-1 score, respectively, 0.93, 0.95, 0.94. The accuracy of oversampling with the Adam and Nadam optimizer is 94%. So, the contribution of this research is by applying bootstrap-based oversampling techniques and adding data augmentation to produce good model performance to be used to classify medical images.
Fake News in Hate Speech Containing Ethnicities, Religions, Races and Intergroup (SARA) on Indonesian Social Media: A Forensic Linguistics Study Agus Syahid; Sutarman Sutarman; Ana Rahmatyar; Dita Meldina; Deshinta Arrova Dewi
Anglophile Journal Vol. 6 No. 1 (2026): Anglophile Journal
Publisher : CV. Creative Tugu Pena

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51278/anglophile.v6i1.2526

Abstract

This study investigates the dissemination of fake news embedded in hate speech containing ethnicity, religion, race, and intergroup (SARA) issues on Indonesian social media from a forensic linguistic perspective. Drawing on speech act theory, the study aims to identify the linguistic forms used in the dissemination of fake news and examine their legal implications. A qualitative method with a forensic linguistic approach was employed. The data consisted of linguistic evidence extracted from eight court cases adjudicated between 2018 and 2020 and obtained from final and legally binding district court decisions available through the Supreme Court Decision Directory of the Republic of Indonesia. Data were analyzed using Searle’s speech act framework, focusing on assertive speech acts. The findings reveal two dominant forms of assertive speech acts in the dissemination of fake news, namely assertive accusations (or slander) and assertive lies. These speech acts were used to promote hate speech, blasphemy, incitement of hatred, and the humiliation or denigration of particular groups based on SARA identities. The study further demonstrates that the dissemination of fake news containing SARA-related hate speech carries significant legal consequences, as perpetrators may be prosecuted under Article 28(2) in conjunction with Article 45A(2) of Law No. 19 of 2016 concerning Electronic Information and Transactions (ITE). The findings contribute to the development of forensic linguistic scholarship by highlighting the relationship between language, misinformation, hate speech, and legal accountability in digital communication.
Co-Authors Agus Syahid Ana Rahmatyar Anggit Larasati Aris Thobirin Dita Meldina Sugiyarto Surono Sutarman Sutarman