Claim Missing Document
Check
Articles

Found 2 Documents
Search

Perbandingan Model Regresi Machine Learning untuk Prediksi Skor Tingkat Stres Berdasarkan Pola Screen Time Tahun 2025 Daffa Pratama Putra; Apriyadi Apriyadi; Zikri Firmansyah; Ken Ditha Tania; Dedy Kurniawan
Jurnal Pendidikan dan Teknologi Indonesia Vol 6 No 4 (2026): JPTI - April 2026
Publisher : CV Infinite Corporation

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52436/1.jpti.1537

Abstract

Transformasi digital yang masif pada era modern telah mendorong peningkatan signifikan dalam durasi paparan layar (screen time), yang diidentifikasi sebagai salah satu faktor risiko utama terhadap kesehatan mental, khususnya peningkatan prevalensi stres psikologis. Metode diagnosis konvensional yang mengandalkan instrumen kuesioner mandiri dinilai kurang optimal karena rentan terhadap bias pelaporan dan bersifat subjektif. Penelitian ini bertujuan untuk membandingkan performa tiga algoritma machine learning, yaitu Random Forest, Support Vector Regression (SVR), dan XGBoost Regression, dalam memprediksi skor tingkat stres secara kontinu (skala 0–10) berdasarkan pola penggunaan perangkat digital. Tahapan penelitian meliputi akuisisi dataset "Screentime vs Mental Wellness Survey 2025" dari repositori publik, pra-pemrosesan data melalui imputasi statistik, normalisasi Min-Max Scaling, dan One-Hot Encoding, dilanjutkan dengan pembangunan model menggunakan evaluasi 10-fold cross-validation serta interpretasi model berbasis metode SHAP. Hasil evaluasi pada data uji menunjukkan bahwa XGBoost merupakan model dengan performa terbaik, mencapai nilai Mean Absolute Error (MAE) terendah sebesar 0,6502, Root Mean Squared Error (RMSE) sebesar 0,8253, dan koefisien determinasi (R²) sebesar 0,8367. Temuan ini mengindikasikan bahwa model mampu menjelaskan lebih dari 83% variasi tingkat stres pada data yang belum pernah dilatih sebelumnya. Analisis feature importance mengungkapkan bahwa indeks kesejahteraan mental dan produktivitas merupakan prediktor paling dominan, sedangkan durasi screen time berkontribusi relatif kecil, yang menunjukkan bahwa faktor psikologis internal lebih berpengaruh terhadap stres dibandingkan intensitas interaksi digital semata. Penelitian ini menyimpulkan bahwa pendekatan ensemble learning, khususnya XGBoost, efektif dalam memodelkan fenomena stres yang bersifat kompleks dan multidimensional sebagai dasar pengambilan keputusan klinis berbasis data.
Analysis and Prediction of MyTelkomsel Complaints Using IndoBERTweet and TimesFM-3 for Service Improvement Prioritization Muhammad Syaikh Azka; Apriansyah Putra; Rahmat Izwan Heroza; Ken Ditha Tania
Brilliance: Research of Artificial Intelligence Vol. 6 No. 4 (2026): Brilliance: Research of Artificial Intelligence, Article Research November 2026
Publisher : Yayasan Cita Cendekiawan Al Khwarizmi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47709/brilliance.v6i4.9879

Abstract

Application reviews contain useful feedback, but the growing volume of Indonesian-language reviews makes manual identification of complaints inefficient, and earlier MyTelkomsel studies stopped at sentiment classification. Objective: This study develops an integrated framework to identify the dominant technical complaints in MyTelkomsel reviews, forecast their trends, and prioritize service improvements. Methods: A total of 51,112 application-related Google Play reviews, published between November 2022 and September 2026, were kept after keyword-based relevance filtering. IndoBERTweet, fine-tuned on the SmSA dataset, performed sentiment analysis, and 44,937 negative reviews were grouped by BERTopic with K-Means into ten complaint categories. TimesFM-3 then produced zero-shot six-month complaint forecasting for each category, which was evaluated with a rolling-origin backtest and used to compute a priority score from forecast load and trend. Results: Login & Account Access, Loading/Performance Issues, and General Bugs/Errors accounted for 55.4% of the negative reviews. After two surge months were excluded, TimesFM-3 reached a weighted absolute percentage error of 54.65% and an 80% interval coverage of 84.42%. Loading/Performance Issues was the only high-priority category (score 74.5), and four categories were medium priority. Problems After Updates was the only medium-priority category with an increasing trend. Conclusion: The framework supports ranking and monitoring of complaint categories. Its moderate accuracy and wide intervals mean that the forecasts should guide priorities rather than predict exact monthly volumes.