Article Per Year (5 Year)
p-Index From 2020 - 2025
0.61
P-Index
This Author published in this journals
All Journal JURIKOM (Jurnal Riset Komputer) Jurnal Algoritma Jurnal Pengabdian Kolaborasi dan Inovasi IPTEKS
Yunika Hardiyanti, Dinna
Unknown Affiliation
Agriculture, Biological Sciences & Forestry Computer Science & IT Control & Systems Engineering Economics, Econometrics & Finance Education Electrical & Electronics Engineering Environmental Science Social Sciences

Published : 3 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 3 Documents
Search

 1 
Perbandingan Kinerja SVM, Random Forest dan XGBoost pada Aplikasi Access by KAI Menggunakkan ADASYN Epriyanti, Nadia; Meiriza, Allsela; Yunika Hardiyanti, Dinna
JURNAL RISET KOMPUTER (JURIKOM) Vol. 12 No. 5 (2025): Oktober 2025
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/jurikom.v12i5.9139

Abstract

The rapid growth of digital applications has heightened the need to understand user perceptions more thoroughly, particularlythrough sentiment analysis of user-generated reviews. In practice, sentiment classification often faces challenges related to class imbalance, especially when neutral reviews are significantly fewer than positive or negative ones. This imbalance can limit a model’s ability to accurately detect all sentiment categories. This study examines the comparative performance of three machine learning algorithmsSupport Vector Machine (SVM), Random Forest (RF), and Extreme Gradient Boosting (XGBoost) by applying the Adaptive Synthetic Sampling (ADASYN) technique to address class imbalance. This study differs from previous similar research by conducting a simultaneous comparative analysis of three algorithms using the ADASYN method in the context of Access by KAIapplication reviews, which has not been examined in prior studies. Experimental results indicate that after implementing ADASYN, model accuracies reached 75.17% for SVM, 84.06% for RF, and 83.17% for XGBoost. Although accuracy slightly decreased after oversampling, the F1-scores for the neutral class improved to 0.13 (SVM), 0.05 (RF), and 0.14 (XGBoost). Before applying ADASYN, the models achieved accuracies of 85.88% (SVM), 85.13% (RF), and 85.37% (XGBoost), but they were unable to effectivelyrecognize neutral sentiments, with F1-scores of 0.00 for SVM and RF, and 0.03 for XGBoost. These findings suggest that ADASYN enhances model sensitivity to neutral sentiment, with XGBoost demonstrating the most consistent and robust performance in sentiment classification for the Access by KAIapplication.
SISTEM RANCANGAN BANGUN SISTEM INFORMASI DESA PADA DESA REBO KABUPATEN BANYUASIN Hardini Novianti; Yunika Hardiyanti, Dinna; Putri Raflesia, Sarifah; Lertarini, Dinda; Rifai, Ahmad; Rossa Indah, Dwi
Jurnal Pengabdian Kolaborasi dan Inovasi IPTEKS Vol. 1 No. 1 (2023): Februari
Publisher : CV. Alina

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (649.934 KB) | DOI: 10.59407/jpki2.v1i1.3

Abstract

Sistem Informasi Desa (SID) merupakan sebuah aplikasi website yang didalamnya memuat tentang informasi data penduduk, layanan publik, produk hukum, dan informasi tentang kegiatan dan program desa yang dikelola oleh pemerintah desa untuk mendukung perkembangan desa menuju desa maju dan mandiri. Secara kuantitatif Kecamatan Rambutan terletak di Kabupaten Banyuasin. Data-data di kantor desa belum terintegrasi secara online sehingga diperlukan adanya website desa untuk mengintegrasikan dan memudahkan dalam mengakses data desa. Kata Kunci : Sistem Informasi Desa (SID)
Penggunaan Delone And Mclean Dalam Mengevaluasi Kesuksesan Sistem Informasi Terhadap E-Ppt Fakultas Ilmu Komputer Universitas Sriwijaya Salsabila, Adella; Yunika Hardiyanti, Dinna
Jurnal Algoritma Vol 22 No 2 (2025): Jurnal Algoritma
Publisher : Institut Teknologi Garut

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33364/algoritma/v.22-2.2955

Abstract

The e-PPT system of the Faculty of Computer Science Universitas Sriwijaya was developed to support online academic administrative services. However, based on observations, users sometimes experience problems such as connection interruptions, a user interface that is not user friendly, and delays in document processing. This study aims to evaluate the success of the e-PPT system implementation using the DeLone and McLean 2003 model with a quantitative approach based on Partial Least Squares Structural Equation Modeling PLS SEM. Data were collected from 353 active students through an online questionnaire, measuring six dimensions namely system quality, information quality, service quality, use, user satisfaction, and net benefits. The results show that information quality and service quality have a significant influence on use and user satisfaction, with service quality being the main driver of system use path coefficient 0.416. Service quality is significant for user satisfaction but not for use p value 0.081. Both use and user satisfaction contribute significantly to net benefits such as time and cost savings. Although the validity and reliability of the instruments were confirmed AVE greater than 0.5 and Cronbachs Alpha greater than 0.7, weaknesses in service quality such as connection errors and a less user friendly interface still need improvement. This study recommends improving administrative responsiveness, simplifying the interface, and adding qualitative analysis for deeper contextual understanding. These findings are relevant for developing more effective academic information systems in higher education institutions.
Co-Authors Ahmad Rifai Allsela Meiriza, Allsela Epriyanti, Nadia Hardini Novianti Lertarini, Dinda Putri Raflesia, Sarifah Rossa Indah, Dwi Salsabila, Adella