cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Wahyuddin
Contact Email
wahyuddin081090@gmail.com
Phone
+6282384091594
Journal Mail Official
jurnalsintakslogika@umpar.ac.id
Editorial Address
Jl.Jend Ahmad Yani KM.6 Kota Parepare Sulawesi Selatan
Location
Kota pare pare,
Sulawesi selatan
INDONESIA
Jurnal Sintaks Logika (JSilog)
Published by Universitas Muhammadiyah Parepare
ISSN : -     EISSN : 2775412X     DOI : -
Core Subject : Science,
Computer Science & IT
Jurnal Sintaks Logika (JSilog) Jurnal Penelitian Ilmiah Teknik Informatika adalah jurnal ilmiah sebagai media kajian ilmiah hasil penelitian, pemikiran dan kajian analisis-kritis mengenai penelitian bidang ilmu komputer dan teknologi. Sebagai bagian dari semangat menyebarluaskan ilmu pengetahuan hasil dari penelitian dan pemikiran untuk pengabdian pada masyarakat luas dan sebagai sumber referensi akademisi di bidang Ilmu Komputer dan Teknologi
Arjuna Subject : Ilmu Komputer (semua kategori) - Ilmu Komputer (Lain-Lain)
Articles 164 Documents
 13   14   15   16   17 
Perbandingan Analisis Sentimen Untuk Prediksi Kepuasan Ulasan Produk Kopi Pada Media Sosial Menggunakan Algoritma Svm Dan Naïve Bayes Pramuja, Trisena; Irawan, Bambang
Jurnal Sintaks Logika Vol. 6 No. 1 (2026): Januari 2026
Publisher : Fakultas Teknik Universitas Muhammadiyah Parepare

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31850/jsilog.v6i1.4284

Abstract

The development of social media has led to a significant increase in the number of consumer reviews of various types of products, including coffee products. To help manufacturers understand consumer satisfaction levels more efficiently, sentiment analysis is a relevant method because it is able to identify opinions automatically. This study compares the performance of two widely used algorithms, namely Support Vector Machine (SVM) and Multinomial Naive Bayes (MNB), in predicting sentiment on consumer reviews related to coffee products on social media. The dataset was analyzed through the stages of text cleanup, TF-IDF transformation, and label encoding process. Both models are developed using a uniform pipeline with consistent parameters to ensure an objective performance comparison. The results show that SVM algorithms with linear kernels produce the highest accuracy compared to Naive Bayes. In addition, a confusion matrix is applied to evaluate the accuracy of predictions in each sentiment category. These findings confirm that SVM is more effective in short-text-based sentiment analysis tasks, such as product reviews on social media platforms.
Pemodelan Analisis Sentimen Ulasan Pengguna Aplikasi Info Bmkg Menggunakan Pendekatan Multinomial Naïve Bayes Syaogi, Moh.; Ramdhan, Nur Ariesanto; Bachri, Otong Saeful; Irawan, Bambang
Jurnal Sintaks Logika Vol. 6 No. 1 (2026): Januari 2026
Publisher : Fakultas Teknik Universitas Muhammadiyah Parepare

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31850/jsilog.v6i1.4285

Abstract

Info BMKG is one of several digital platforms that have been pushed by the fast evolution of IT to replace traditional methods of providing public services. Reviews on the Play Store can be used to determine user perceptions and levels of satisfaction with the application. Manual analysis is laborious and inefficient due to the high number of evaluations. Consequently, the purpose of this research is to use the Naive Bayes algorithm to categorize evaluations of the Info BMKG app as either positive or negative in order to do sentiment analysis. Using a web scraping approach, a total of 5,000 user evaluations were obtained for the study data. Next, the data underwent text preprocessing, word weighting using the TF-IDF technique, and sentiment classification with the Multinomial Naive Bayes algorithm. There was an 80:20 split between the dataset's training and testing sets. The experimental findings show that the Naive Bayes algorithm achieves an accuracy of 87.83% on the testing data when it comes to classifying user review emotions.
Prediksi Kanker Payudara Berbasis Machine Learning Dengan Analisis Probabilitas Klasisfikasi ardyansyah, luthfi; Irawan, Bambang
Jurnal Sintaks Logika Vol. 6 No. 1 (2026): Januari 2026
Publisher : Fakultas Teknik Universitas Muhammadiyah Parepare

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31850/jsilog.v6i1.4294

Abstract

Breast cancer is one of the diseases with a high mortality rate in women, so early detection is crucial to increase the chances of recovery. Unfortunately, conventional methods of diagnosis still rely on the interpretation of medical personnel and laboratory procedures which are time-consuming and costly. This study tries to present a machine learning-based approach to predict breast cancer, while adding a classification probability analysis to make the prediction more informative. The breast cancer dataset was used to train four models, namely Logistic Regression, Support Vector Machine, Random Forest, and K-Nearest Neighbor. Evaluation was carried out using accuracy, confusion matrix, ROC curve, and AUC. The results showed that all four models were able to classify cancers with fairly high performance, while one model stood out with the highest accuracy and AUC values. Classification probability analysis provides additional perspective on the confidence level of predictions, which can help medical personnel make more objective clinical decisions.
Analisis Pola Konsumsi Energi Listrik Pelanggan Rumah Tangga Menggunakan Alogaritma K-Means Clustering Hilmi Mubarok; Irawan, Bambang
Jurnal Sintaks Logika Vol. 6 No. 1 (2026): Januari 2026
Publisher : Fakultas Teknik Universitas Muhammadiyah Parepare

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31850/jsilog.v6i1.4296

Abstract

The increase in household electricity consumption is one of the main challenges in national energy management. Diverse electricity usage patterns are influenced by social, economic, and behavioral characteristics of consumers. This study aims to analyze and cluster household electricity consumption patterns using the K-Means Clustering algorithm. The dataset consists of secondary data from 1,200 household customers with attributes including installed power capacity, monthly electricity consumption (kWh), peak usage time, and average daily load. The research stages include data cleaning, normalization using StandardScaler, determination of the optimal number of clusters using the Elbow Method, clustering with K-Means, and evaluation using the Davies-Bouldin Index (DBI). The results indicate that the optimal number of clusters is three, representing low, medium, and high electricity consumption groups. A DBI value of 0.71 indicates good clustering quality. These findings can support electricity providers in designing energy efficiency policies and household load management strategies.

Page 17 of 17 | Total Record : 164

 13   14   15   16   17 

Filter by Year

2021 2026


Reset
Filter By Issues
All Issue Vol. 6 No. 1 (2026): Januari 2026 Vol. 5 No. 3 (2025): September 2025 Vol. 5 No. 2 (2025): Mei 2025 Vol. 5 No. 1 (2025): Januari 2025 Vol. 4 No. 3 (2024): September 2024 Vol. 4 No. 2 (2024): Mei 2024 Vol. 4 No. 1 (2024): Januari 2024 Vol. 3 No. 3 (2023): September 2023 Vol. 3 No. 2 (2023): Mei 2023 Vol. 3 No. 1 (2023): Januari 2023 Vol. 2 No. 3 (2022): September 2022 Vol. 2 No. 2 (2022): Mei 2022 Vol. 2 No. 1 (2022): Januari 2022 Vol. 1 No. 3 (2021): Oktober 2021 Vol. 1 No. 2 (2021): Mei 2021 Vol. 1 No. 1 (2021): Januari 2021 Vol 1 No 1 (2021): Januari 2021 More Issue