Claim Missing Document
Check
Articles

Found 2 Documents
Search

SENTIMENT ANALYSIS APPROACH TO USER PERCEPTIONS OF AMMANA SHARIA FINTECH BASED ON MACHINE LEARNING ALGORITHMS Farida Islamiah; Isma Muthahharah
Jurnal Ekonomi Ichsan Sidenreng Rappang Vol 4 No 2 (2025): September-December
Publisher : Universitas Ichsan Sidenreng Rappang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.61912/jeinsa.v4i2.289

Abstract

Penelitian ini bertujuan untuk menganalisis dan mengklasifikasikan sentimen pengguna terhadap aplikasi fintech syariah Ammana yang diunduh dari Google Play Store. Data penelitian diperoleh melalui proses web scraping terhadap komentar pengguna, kemudian dilakukan pra-pemrosesan teks meliputi case folding, stopword removal, stemming, dan tokenisasi menggunakan pustaka Sastrawi pada bahasa pemrograman Python melalui Google Colab. Penelitian menggunakan pendekatan kuantitatif komparatif dengan membandingkan tiga algoritma machine learning, yaitu Support Vector Classifier (SVC), Multinomial Naive Bayes (MNB), dan Random Forest (RF). Hasil klasifikasi menunjukkan bahwa SVC memiliki performa terbaik dengan nilai akurasi 91,80%, presisi 92,67%, recall 91,80%, dan F1-score 91,99%. Sementara itu, Random Forest menempati posisi kedua dengan akurasi 87,98%, sedangkan Naive Bayes memperoleh nilai terendah dengan akurasi 85,24%. Secara keseluruhan, temuan ini mengindikasikan bahwa algoritma SVC paling efektif dalam mendeteksi sentimen positif, negatif, dan netral pengguna terhadap aplikasi Ammana. Dari perspektif bisnis dan industri financial technology (fintech), hasil ini menunjukkan bahwa analisis sentimen dapat digunakan sebagai alat strategis untuk memantau persepsi publik, meningkatkan pengalaman pengguna (user experience), serta memperkuat kepercayaan terhadap layanan keuangan digital berbasis syariah.
The Impact of Malnutrition on Infant Mortality Rate in Indonesia: A Spline Regression Approach Isma Muthahharah; Rahmat Hidayat
Journal of Mathematics, Computations and Statistics Vol. 8 No. 2 (2025): Volume 08 Nomor 02 (Oktober 2025)
Publisher : Jurusan Matematika FMIPA UNM

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35580/jmathcos.v8i2.9351

Abstract

The Infant Mortality Rate (IMR) in Indonesia is still an important index in assessing the quality of public health. One aspect that is thought to influence the high IMR is malnutrition. One of the objectives of this study is to analyze the relationship between malnutrition and IMR through a nonparametric spline regression approach. The data used in this study are secondary data obtained from the Central Statistics Agency in 2022 with the IMR variable as the dependent variable and the percentage of malnutrition as the independent variable. The spline regression model was chosen because it is able to capture the nonlinear relationship between the variables analyzed. Based on the research results that have been obtained, we can see that the best model is spline regression, namely by selecting three knot points, the coefficient of determination (R^2) value is 23,27%. However, this model still has limitations, such as violations of residual assumptions. Therefore, it is hoped that further research will add or select other variables that may be more relevant in order to improve the quality of the model.