Article Per Year (5 Year)
p-Index From 2021 - 2026
0.408
P-Index
This Author published in this journals
All Journal Progresif: Jurnal Ilmiah Komputer
Maulana, Donny
Universitas Pelita Bangsa
Computer Science & IT Control & Systems Engineering

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

Found 2 Documents
Search

 1 
Analisis Sentimen Terhadap Program Makan Bergizi Gratis Menggunakan Metode Logistic Regression Indrawan, Ari Budi; Maulana, Donny; Abdurrohman, M. Zubair
Progresif: Jurnal Ilmiah Komputer Vol 22, No 2 (2026): April
Publisher : STMIK Banjarbaru

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35889/progresif.v22i2.3610

Abstract

This study aims to analyze public sentiment toward the Free Nutritious Meal Program (MBG), a policy implemented by the Indonesian government to improve the nutritional quality of students. The data used consist of 1,440 tweets collected through a scraping process from the X/Twitter platform. The data processing stages include preprocessing steps such as case folding, cleaning, tokenizing, stopword removal, and stemming using the Sastrawi library. Furthermore, the text data are transformed into numerical representations using the TF-IDF method and classified using the Logistic Regression algorithm. To enhance the model's performance, the SMOTE technique is applied to address data imbalance, along with GridSearchCV for parameter optimization. The results indicate that the Logistic Regression model achieves excellent performance, with an Accuracy of 98.96%, Precision of 99.14%, Recall of 98.10%, and an F1-Score of 98.61%. This study is expected to provide an objective overview of public perception and serve as a reference for policy evaluation and decision-making.Keywords: Sentiment Analysis; Free Nutritious Meal Program; Logistic Regression; Text mining; NLP.AbstrakPenelitian ini bertujuan untuk menganalisis sentimen masyarakat terhadap Program Makan Bergizi Gratis (MBG) yang merupakan kebijakan pemerintah Indonesia dalam meningkatkan kualitas gizi peserta didik. Data yang digunakan berupa 1.440 tweet yang diperoleh melalui proses scraping dari platform X/Twitter. Tahapan pengolahan data meliputi preprocessing yang terdiri dari case folding, cleaning, tokenizing, stopword removal, dan stemming menggunakan library Sastrawi. Selanjutnya, data teks diubah menjadi representasi numerik menggunakan metode TF-IDF dan diklasifikasikan menggunakan algoritma Logistic Regression. Untuk meningkatkan performa model, diterapkan teknik SMOTE dalam mengatasi ketidakseimbangan data serta GridSearchCV untuk optimasi parameter. Hasil penelitian menunjukkan bahwa model Logistic Regression memiliki kinerja yang sangat baik dengan akurasi sebesar 98,96%, Precision 99,14%, Recall 98,10%, dan F1-Score 98,61%. Penelitian ini diharapkan dapat memberikan gambaran objektif mengenai persepsi masyarakat serta menjadi bahan evaluasi dalam pengambilan kebijakan.Kata kunci: Analisis Sentimen; Makan Bergizi Gratis; Logistic Regression; Text mining; NLP.
Analisis Klasifikasi Risiko Penyakit Jantung Menggunakan Metode Random Forest Damayanti, Alfina; Maulana, Donny; Abdurrohman, M. Zubair
Progresif: Jurnal Ilmiah Komputer Vol 22, No 2 (2026): April
Publisher : STMIK Banjarbaru

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35889/progresif.v22i2.3609

Abstract

Heart disease is one of the leading causes of death worldwide, making early detection crucial to reduce the risk of complications and mortality. The advancement of machine learning technology enables fast and accurate analysis of medical data to support the diagnostic process. This study aims to develop a classification model for heart disease risk using the Random Forest algorithm. The dataset used is the Heart Disease Dataset from Kaggle, consisting of 1,025 patient records with 14 medical attributes, such as age, gender, blood pressure, cholesterol level, and maximum heart rate. The methodology applied is CRISP-DM, which includes Data Understanding, Data Preparation, Modeling, Evaluation, and Deployment. Model Evaluation is conducted using a confusion matrix, cross-validation, and ROC-AUC. The results show that the Random Forest algorithm achieves a high Accuracy of 99.96% and a cross-validation score of 0.996. The variables chest pain, ca, and thalach are identified as the most influential factors in the prediction.Keywords: Heart Disease; Random Forest; Machine learning; Classification; CRISP-DM AbstrakPenyakit jantung merupakan salah satu penyebab utama kematian di dunia sehingga deteksi dini sangat penting untuk mengurangi risiko komplikasi dan kematian. Perkembangan teknologi machine learning memungkinkan analisis data medis secara cepat dan akurat dalam membantu proses diagnosis. Penelitian ini bertujuan membangun model klasifikasi risiko penyakit jantung menggunakan Algoritma Random Forest. Dataset yang digunakan adalah Heart Disease Dataset dari Kaggle yang terdiri dari 1025 data pasien dengan 14 atribut medis, seperti usia, jenis kelamin, tekanan darah, kadar kolesterol, dan detak jantung maksimum. Metode yang digunakan adalah CRISP-DM meliputi Data Understanding, Data Preparation, Modeling, Evaluation, dan Deployment. Evaluasi model dilakukan menggunakan confusion matrix, cross validation, dan ROC-AUC. Hasil penelitian menunjukkan bahwa Random Forest menghasilkan akurasi tinggi dengan nilai 99,96% serta cross validation sebesar 0,996. Variabel chest pain, ca, dan thalach menjadi faktor paling berpengaruh dalam prediksi.Kata kunci: Penyakit jantung; Random Forest; Machine learning; Klasifikasi; CRISP-DM.
Co-Authors Abdurrohman, M. Zubair Damayanti, Alfina Indrawan, Ari Budi