Article Per Year (5 Year)
p-Index From 2021 - 2026
2.17
P-Index
This Author published in this journals
All Journal Syntax Literate: Jurnal Ilmiah Indonesia Journal of Electrical Engineering and Computer (JEECOM) Jurnal Dinamika Informatika (JDI) Jurnal Manajemen Sistem Informasi Jurnal Pengembangan Teknologi Informasi dan Komunikasi (JUPTIK) Jurnal Informatika Medis (J-INFORMED)
Sidik Praptomo
Universitas Muhammadiyah Muara Bungo
Humanities Computer Science & IT Control & Systems Engineering Education Electrical & Electronics Engineering Energy Engineering Environmental Science Health Professions Law, Crime, Criminology & Criminal Justice Library & Information Science Nursing Public Health Social Sciences Veterinary Other

Published : 13 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 13 Documents
Search

 1   2 
Menganalisis Sentimen Ulasan i.Saku E-Wallet Play Store Menggunakan Support Vector Machine Suryanto; Sidik Praptomo
Jurnal Dinamika Informatika Vol. 14 No. 2 (2025): Vol. 14 No. 2 (2025)
Publisher : Program Studi Informatika Universitas PGRI Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31316/jdi.v14i2.402

Abstract

The digital era has transformed lifestyles, with people increasingly relying on electronic devices as tools for everyday life. Technology simplifies various activities by streamlining data and information processing. The growing demand for data has driven the development of new technologies to process information quickly. Technological advancements have improved transportation, access to information, education, and the convenience of online transactions, particularly through digital wallets or e-wallets. Digital financial services, including e-wallets, facilitate easy transactions using e-wallet funds. The primary reason for their use is the convenience of electronic wallets, which eliminate the need for cash and simplify transactions for both buyers and sellers. The case of i.Saku demonstrates its popularity, with over 5 million downloads on the Google Play Store since 2017. Google's digital platform, Google Play Store, includes user reviews as a valid source of information. Nearly 50% of internet users rely on recommendations from other users before using a product. Google Play Store reviews influence the decisions of potential users, but managing them manually is not easy. Sentiment analysis, or opinion mining, is the study of opinions, behaviors, and feelings of individuals towards an entity and is crucial for understanding user reviews. In the context of i.Saku, this research focuses on sentiment analysis of Google Play Store reviews using support vector machine techniques. The study outlines the stages from preprocessing to sentiment analysis, highlighting the complexity and benefits of technology-based sentiment analysis.
Design and Evaluation of a Web-Based Geographic Information System for PPDB Promotion Zoning Based on Student-Origin Distributions Riko Muhammad Suri; Ahmad Risman; Sidik Praptomo
Journal of Electrical Engineering and Computer (JEECOM) Vol 7, No 2 (2025)
Publisher : Universitas Nurul Jadid

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33650/jeecom.v7i2.12706

Abstract

Advances in information technology have accelerated the digitalization of educational services, including Indonesia’s student admission process (PPDB). This study designs and evaluates a web-based Geographic Information System (GIS) to map student-origin distributions and construct promotion zones that guide PPDB outreach strategies. The system was built with CodeIgniter and Leaflet for interactive mapping, while applicant addresses/school origins were processed via geocoding. Outputs include point maps, density heatmaps, administrative-area aggregation (urban village/sub-district), and simple distance buffers (e.g., 1–3 km) to derive rule-based priority promotion zones (thresholds on density and proximity to the school). Evaluation comprised functional testing (black box) and user assessments using questionnaires (Likert/SUS). Results indicate that the system expedites registration, reduces the risk of data loss, simplifies data summarization, and provides promotion-zoning maps that help committees target outreach more effectively. The contributions are: (1) a PPDB web-GIS model that combines origin mapping with rule-based promotion zoning, (2) a replicable operational workflow, and (3) recommendations for future work, including advanced analytics dashboards and automated notifications
Explainable Machine Learning for Predicting Student Dropout and Academic Success Using XGBoost and SHAP Sidik Praptomo; Ahmad Risman; Riko Muhammad Suri
Journal of Electrical Engineering and Computer (JEECOM) Vol 8, No 1 (2026)
Publisher : Universitas Nurul Jadid

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33650/jeecom.v8i1.16978

Abstract

Student dropout is a persistent challenge in higher education, and predictive models can support early identification of students who may require academic or financial intervention. This study develops an explainable multiclass machine learning approach to predict three academic outcomes—Dropout, Enrolled, and Graduate—using the public Predict Students' Dropout and Academic Success dataset containing 4,424 student records. Logistic Regression, Random Forest, and Extreme Gradient Boosting (XGBoost) were compared using a stratified 80:20 hold-out design. XGBoost hyperparameters were optimized through randomized search with five-fold stratified cross-validation, and SHapley Additive exPlanations (SHAP) were used to interpret global and class-specific predictions. Random Forest achieved the highest overall accuracy of 77.18%, whereas the optimized XGBoost model produced the highest macro recall of 69.58% and macro F1-score of 70.08%. XGBoost improved recall for the minority Enrolled class to 46.54%, compared with 38.36% for Random Forest and 33.33% for Logistic Regression. SHAP analysis identified the number of curricular units approved in the second and first semesters, tuition-fee status, course, second-semester grade, and age at enrollment among the most influential predictors. Low academic progression and unpaid tuition status contributed strongly toward Dropout predictions, while stronger academic progression shifted predictions toward Graduate. These findings show that explainability complements predictive performance by revealing actionable patterns behind multiclass student-outcome predictions.Student dropout is a persistent challenge in higher education, and predictive models can support early identification of students who may require academic or financial intervention. This study develops an explainable multiclass machine learning approach to predict three academic outcomes—Dropout, Enrolled, and Graduate—using the public Predict Students' Dropout and Academic Success dataset containing 4,424 student records. Logistic Regression, Random Forest, and Extreme Gradient Boosting (XGBoost) were compared using a stratified 80:20 hold-out design. XGBoost hyperparameters were optimized through randomized search with five-fold stratified cross-validation, and SHapley Additive exPlanations (SHAP) were used to interpret global and class-specific predictions. Random Forest achieved the highest overall accuracy of 77.18%, whereas the optimized XGBoost model produced the highest macro recall of 69.58% and macro F1-score of 70.08%. XGBoost improved recall for the minority Enrolled class to 46.54%, compared with 38.36% for Random Forest and 33.33% for Logistic Regression. SHAP analysis identified the number of curricular units approved in the second and first semesters, tuition-fee status, course, second-semester grade, and age at enrollment among the most influential predictors. Low academic progression and unpaid tuition status contributed strongly toward Dropout predictions, while stronger academic progression shifted predictions toward Graduate. These findings show that explainability complements predictive performance by revealing actionable patterns behind multiclass student-outcome predictions.
Co-Authors Ahmad Risman Alfianto, Dafit Almaknun, Indi Lulu Ayona A., Nur Badriah, Siti Robi’ahtu DAFIT AFIANTO Dodi Putra Domy Kristomo, Domy Erza, Desi Metriana Fitriani, Yessy Hermanto Hermanto Ika Safitri Windiarti Indah Ayu Lestari, Indah Ayu Insani, Indah Jasmir, Jasmir Karlinda Kurniawan, Jefdy Nurohman, Muhammad Pebriani, Amelia Puspita, Sella Ramanda, Febri Rianingsih, Hizkia Hendra Riko Muhammad Suri Riko Muhammad Suri Risti Afriyani Afriyani Suryanto Suryanto Suryanto Wibowo, Hendry