Claim Missing Document
Check
Articles

Analisis Performa Metode Machine Learning dalam Mengidentifikasi Penyebab Ulasan Rating Satu Aplikasi MyBluebird Azziizah, Almira Farradinda; Mustofa, Hery; Umam, Khothibul; Handayani, Maya Rini
Jurnal Ilmiah Global Education Vol. 6 No. 4 (2025): JURNAL ILMIAH GLOBAL EDUCATION
Publisher : LPPM Institut Pendidikan Nusantara Global

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55681/jige.v6i4.4704

Abstract

This study addresses the increasing prevalence of negative user reviews for the MyBluebird ride-hailing application, focusing on the identification and classification of the main causes of one-star ratings. The research aims to compare the effectiveness of Support Vector Machine, Random Forest, and Naïve Bayes algorithms in classifying user complaints. Employing a quantitative experimental approach, the study utilizes a dataset of 1,399 one-star reviews collected purposively from Google Play Store. Data preprocessing includes cleaning, tokenization, and feature extraction using TF-IDF. The classification models are evaluated using accuracy, precision, recall, and F1-score metrics. Results indicate that Random Forest achieves the highest accuracy (90%), outperforming the other algorithms, with bugs/errors as the most frequent complaint, followed by driver performance, other issues, and price. The study concludes that machine learning-based classification can effectively map user dissatisfaction, though data imbalance remains a limitation. Future research should apply data balancing techniques and expand the dataset for broader generalization. Practical implications suggest that developers can utilize automated classification to improve service quality and address user needs more efficient.
Digital innovation in islamic guidance: Fuzzy mamdani-based stress level detection for muslim adolescents Amal, Muhammad Niltal; Handayani, Maya Rini
Jurnal Ilmu Dakwah Vol. 45 No. 2 (2025)
Publisher : Faculty of Dakwah and Communication, Walisongo State Islamic University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21580/jid.v45.2.28875

Abstract

Purpose - The purpose of this study is to address the urgent need for a reliable and accessible preliminary assessment tool for mental health issues among Indonesian adolescents, a demographic significantly impacted by recent societal changes and showing high rates of psychological distress (e.g., 34.9% experiencing mental problems per I-NAMHS 2022) Method - The methodology employed is the design and development of a web-based expert system utilizing Fuzzy Logic to diagnose stress symptoms. The system is structured with four core components (User Interface, Knowledge Base, Inference Mechanism, Working Memory) and incorporates Fuzzy Tsukamoto/Mamdani/Sugeno principles for mapping firm numerical symptom inputs to linguistic variables through Fuzzification and Defuzzification processes. Result  -  The result (anticipated/achieved) is a functional, dual-role web system (Admin/User) capable of providing objective, preliminary stress categorization, thereby serving as a first step toward early intervention. Implication – The implication of this work is twofold: clinically, it provides an immediate, non-expert-dependent tool for initial screening; ethically and religiously, it supports the collective obligation (fard kifayah) to safeguard youth mental well-being and maintain their fitrah. Originality/Value - The originality of this research lies in the specific integration of Fuzzy Logic reasoning within a web-based expert system tailored explicitly to the Indonesian adolescent context for stress awareness and preliminary diagnosis.*** Tujuan - Tujuan studi ini adalah untuk memenuhi kebutuhan mendesak akan alat penilaian awal yang andal dan mudah diakses untuk masalah kesehatan mental di kalangan remaja Indonesia, kelompok demografis yang sangat terdampak oleh perubahan sosial terkini dan menunjukkan tingkat gangguan psikologis yang tinggi (misalnya, 34,9% mengalami masalah mental menurut I-NAMHS 2022) Metode - Metode yang digunakan adalah desain dan pengembangan sistem pakar berbasis web yang memanfaatkan Logika Fuzzy untuk mendiagnosis gejala stres. Sistem ini terdiri dari empat komponen inti (Antarmuka Pengguna, Basis Pengetahuan, Mekanisme Inferensi, Memori Kerja) dan mengintegrasikan prinsip-prinsip Fuzzy Tsukamoto/Mamdani/Sugeno untuk memetakan masukan numerik gejala yang pasti ke variabel linguistik melalui proses Fuzzifikasi dan Defuzzifikasi. Hasil - Hasil (diperkirakan/tercapai) adalah sistem web fungsional dengan dua peran (Admin/Pengguna) yang mampu memberikan kategorisasi stres awal yang objektif, sehingga berfungsi sebagai langkah awal menuju intervensi dini. Implikasi – Implikasi dari penelitian ini dua arah: secara klinis, menyediakan alat skrining awal yang segera dan tidak bergantung pada ahli; secara etis dan agama, mendukung kewajiban kolektif (fard kifayah) untuk melindungi kesejahteraan mental remaja dan menjaga fitrah mereka. Orisinalitas/Nilai - Keaslian penelitian ini terletak pada integrasi spesifik logika fuzzy dalam sistem pakar berbasis web yang dirancang khusus untuk konteks remaja Indonesia dalam kesadaran stres dan diagnosis awal.