Article Per Year (5 Year)
p-Index From 2021 - 2026
0.444
P-Index
This Author published in this journals
All Journal Kohesi: Jurnal Sains dan Teknologi Jurnal Ilmu Komputer dan Informatika
Garamba, Yafianus
Unknown Affiliation
Biochemistry, Genetics & Molecular Biology Chemical Engineering, Chemistry & Bioengineering Computer Science & IT Education Electrical & Electronics Engineering Energy Engineering Mathematics Other

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

Found 2 Documents
Search

 1 
ANALISIS SENTIMEN ULASAN PENGGUNA BINANCE DI GOOGLE PLAY MENGGUNAKAN ALGORITMA NAÏVE BAYES DAN SUPPORT VECTOR MACHINE DENGAN TEKNIK SMOTE Fahlapi, Riza; Hafid, Danang Abu; Abdurrazaq, Abdurrazaq; Abulkhoir, Moh. Azam; Kurniawan, Bebi; Garamba, Yafianus
Kohesi: Jurnal Sains dan Teknologi Vol. 6 No. 11 (2025): Kohesi: Jurnal Sains dan Teknologi
Publisher : CV SWA Anugerah

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.3785/kohesi.v6i11.10616

Abstract

Penelitian ini bertujuan untuk menganalisis sentimen ulasan pengguna aplikasi Binance di Google Play menggunakan dua algoritma pembelajaran mesin, yaitu Naïve Bayes (NB) dan Support Vector Machine (SVM). Untuk menangani masalah ketidakseimbangan kelas dalam data, diterapkan teknik SMOTE (Synthetic Minority Over-sampling Technique). Data yang digunakan dalam penelitian ini diambil dengan metode web scraping pada ulasan aplikasi Binance, dengan data yang disaring berdasarkan ulasan terbaru dan rating. Hasil eksperimen menunjukkan bahwa dengan penerapan SMOTE, baik algoritma Naïve Bayes maupun SVM memberikan peningkatan yang signifikan pada akurasi serta metrik evaluasi lainnya seperti precision, recall, dan F1-score. Secara keseluruhan, penelitian ini menunjukkan bahwa teknik SMOTE efektif dalam menangani ketidakseimbangan kelas pada analisis sentimen ulasan aplikasi. This study aims to analyze the sentiment of Binance app user reviews on Google Play using two machine learning algorithms, namely Naïve Bayes (NB) and Support Vector Machine (SVM). To overcome the problem of class imbalance in the data, the SMOTE (Synthetic Minority Over-sampling Technique) technique is applied. The data used in this study was taken using the web scraping method on Binance app reviews, with data filtered based on the latest reviews and ratings. The experimental results show that with the application of SMOTE, both the Naïve Bayes and SVM algorithms provide significant improvements in accuracy and other evaluation metrics such as precision, recall, and F1-score. Overall, this study shows that the SMOTE analysis technique is effective in handling class synchrony in app review sentiment.
Klasifikasi Penyakit Asma Menggunakan Algoritma Decision Tree Pada Rapidminer Ardhiyansyah, Pramudhitya; ., Abdurrazzaq; Alfiansyah, Afif; Hilmy Riwanto, Muhammad; Gultom, Sahdia; Shipa, Erna Grace; Ramdani Koswara, Mochamad Fauzi; Garamba, Yafianus
Jurnal Ilmu Komputer dan Informatika | E-ISSN : 3063-9026 Vol. 2 No. 3 (2026): Januari - Maret
Publisher : GLOBAL SCIENTS PUBLISHER

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Asthma is a disease characterized by chronic inflammation of the respiratory system with a relatively high recurrence rate in Indonesia. This condition highlights the need for a data-driven approach to support a more objective and systematic disease classification process. This study aims to classify asthma by applying the Decision Tree algorithm, which is implemented using RapidMiner software as an analytical tool. This research adopts the CRISP-DM framework as the research workflow, encompassing the stages of problem understanding, data understanding, data preparation, modeling, evaluation, and deployment. The dataset used is secondary data obtained from the Kaggle platform, with an initial total of 10,000 patient records. During the data preparation stage, data cleaning, transformation, feature selection, and class imbalance handling were performed, resulting in 4,866 data instances used for modeling. The evaluation results indicate that the Decision Tree model achieved an accuracy of 93.63%, with a precision value of 89.72% and a recall value of 98.56% for the asthma class. In addition to its strong performance, the resulting model is easily interpretable through clear decision rules, making it suitable as a decision-support tool for asthma disease classification.
Co-Authors ., Abdurrazzaq Abdurrazaq Abdurrazaq, Abdurrazaq Abulkhoir, Moh. Azam Alfiansyah, Afif Ardhiyansyah, Pramudhitya Fahlapi, Riza Gultom, Sahdia Hafid, Danang Abu Hilmy Riwanto, Muhammad Kurniawan, Bebi Ramdani Koswara, Mochamad Fauzi Shipa, Erna Grace