Article Per Year (5 Year)
p-Index From 2021 - 2026
0.408
P-Index
This Author published in this journals
All Journal Jurnal Pengabdian Masyarakat Multidisiplin Jurnal Algoritma
Cherliana
Universitas Sriwijaya
Aerospace Engineering Humanities Astronomy Automotive Engineering Biochemistry, Genetics & Molecular Biology Chemistry Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering Earth & Planetary Sciences Education Electrical & Electronics Engineering Energy Environmental Science Immunology & microbiology Law, Crime, Criminology & Criminal Justice Materials Science & Nanotechnology Mathematics Medicine & Pharmacology Nursing Public Health Social Sciences Other

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

Found 2 Documents
Search

 1 
Penerapan Random Forest dan XGBoost untuk Analisis Sentimen pada Ulasan Aplikasi M-Pajak Cherliana; M. Rudi Sanjaya; Dwi Rosa Indah; Dedy Kurniawan
Jurnal Algoritma Vol 23 No 1 (2026): Jurnal Algoritma
Publisher : Institut Teknologi Garut

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33364/algoritma/v.23-1.3370

Abstract

This study aims to evaluate the quality of digital tax services by analyzing the sentiment expressed in user reviews of the M-Pajak app. A dataset of 6,829 reviews was classified into negative, neutral, and positive sentiment, and the study tested the performance of the Random Forest and XGBoost algorithms. Although the test results showed high accuracy rates of 85.21% in the hold-out validation scheme and 90.14% in stratified k-fold cross-validation, an in-depth evaluation using a confusion matrix revealed significant model bias toward the majority class. Key findings indicate that these accuracy figures are misleading because both models completely failed to classify the neutral class, yielding extremely low F1-scores (0.00–0.11). This phenomenon confirms that the primary issue lies not in algorithm selection, but in the extreme data distribution imbalance and the ambiguity of rating-based labeling. The scientific contribution of this research lies in demonstrating that the evaluation of sentiment classification systems must go beyond conventional accuracy metrics. By prioritizing performance stability across each class, the resulting system is expected to provide fairer and more objective evaluation results for public data.
PENGEMBANGAN PENDAMPINGAN PEMBUATAN SISTEM INFORMASI PELAPORAN SARANA DAN PRASARANA TK ISLAM AISYAH DESA MUARA PENIMBUNG ULU m.rudi sanjaya; endang lestari ruskan; Dwi Rosa Indah; Bayu Wijaya Putra; Hasnan Afif; Gabriel Ekoputra Hartono Cahyadi; Ardina Ariani; Dimas Anwar; Naufal Rafif Pratama; M. Ghalib Assidiq Gusri; Cherliana; Riza Aqilah Nashifah; Salsa Yurinka; M. Yusuf; Dinda Misi Islami; Syawaluddin Boy Rambe-Al-Ayyubi; Ulva Khairunisa
Jurnal Pengabdian Masyarakat Multidisiplin Vol 10 No 1 (2026): Oktober
Publisher : LPPM Universitas Abdurrab

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36341/jpm.v10i1.8569

Abstract

This community service activity was initiated in response to the need at TK Islam Aisyah in Muara Penimbung Ulu Village to improve the reporting of school facilities and infrastructure. To date, facility data have been recorded in logbooks and separate documents. This approach makes it time-consuming for school administrators to check inventory quantities, assess facility conditions, locate damage records, and prepare reports. The activity aimed to help the partner develop and use a web-based reporting information system while strengthening administrators’ ability to manage data digitally. The activity involved observation, interviews, needs assessment, system design, functional testing, training, mentoring, and joint evaluation with the partner. The resulting system enables users to record item details and locations, update facility conditions, upload documentation of damage, record follow-up actions, and compile summary reports. User testing showed that the system’s main functions operated in accordance with the school administrators’ needs. The mentoring sessions also helped participants learn to add, search, update, and present data with less reliance on the implementation team. The system helps keep facility information organized and easy to retrieve. This information can support decisions about facility maintenance, repairs, and procurement. Participants’ understanding was assessed through pretests and posttests conducted over three days, with 29 participants on day one, 25 on day two, and 27 on day three. The average scores increased from 32.76 to 62.76 on day one, from 52.00 to 80.80 on day two, and from 46.67 to 88.89 on day three. The corresponding average N-Gain scores were 0.407, 0.579, and 0.783. Testing indicated that the system’s main functions met the partner’s needs. Because there was no control group and participant identities across the three days were unavailable, score changes are reported descriptively and do not establish a causal effect. Overall, the activity helped improve administrators’
Co-Authors Ardina Ariani Bayu Wijaya Putra Dedy Kurniawan Dimas Anwar Dinda Misi Islami Dwi Rosa Indah Endang Lestari Ruskan Gabriel Ekoputra Hartono Cahyadi Hasnan Afif M. Ghalib Assidiq Gusri M. Rudi Sanjaya M. Yusuf m.rudi sanjaya Naufal Rafif Pratama Riza Aqilah Nashifah Salsa Yurinka Syawaluddin Boy Rambe-Al-Ayyubi Ulva Khairunisa