Article Per Year (5 Year)
p-Index From 2021 - 2026
0.983
P-Index
This Author published in this journals
All Journal JURNAL MEDIA INFORMATIKA BUDIDARMA Jurnal Sistem Komputer dan Informatika (JSON) Bulletin of Computer Science Research
Rahmat Rahmat
Universitas Buana Perjuangan Karawang, Karawang
Computer Science & IT Control & Systems Engineering Electrical & Electronics Engineering

Published : 5 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 5 Documents
Search

 1 
Komparasi Algoritma Naïve Bayes Dan Support Vector Machine (SVM) Pada Analisis Sentimen Spotify Ayu Sri Rahayu; Ahmad Fauzi; Rahmat Rahmat
Jurnal Sistem Komputer dan Informatika (JSON) Vol 4, No 2 (2022): Desember 2022
Publisher : STMIK Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/json.v4i2.5398

Abstract

The Spotify app is a subject of interest to social networking communities with significant disagreements or sentiments. Sentiment Analysis is a solution to automatically categorize opinions or ratings into negative or positive opinions. The techniques used in this research are Support Vector Machines (SVM) and Naïve Baye. The advantages of Naïve Bayes are simple, fast and high accuracy. SVM, on the other hand, can identify different hyperplanes that maximize the margin between two different classes. The classification results of this study have two category labels, namely negative and positive. The resulting accuracy value indicates the best test model for sentiment classification cases. Accuracy is measured by the confusion matrix and the results show that the accuracy value of the SVM algorithm is 84% while the accuracy value of the Naïve Bayes algorithm is higher than SVM which is 86.4%.
Penerapan Convolutional Neural Network pada Timbangan Pintar Menggunakan ESP32-CAM Hanung Pangestu Rahman; Jamaludin Indra; Rahmat Rahmat
JURNAL MEDIA INFORMATIKA BUDIDARMA Vol 7, No 1 (2023): Januari 2023
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/mib.v7i1.5469

Abstract

Scales are needed by traders, including vegetable traders, but the scales created in the market can only determine the weight. That way traders need time to calculate the price based on the weight and type of vegetables. In previous research there has been research on smart scales that can calculate the total price based on the weight and type of vegetables being weighed, this study used the Raspberry Pi 3 Model B and the Convolutional Neural Network (CNN) as a method for the scales to be able to identify the types of vegetables that are on it. Along with the rapid development of technology, the price of the Raspberry Pi for all variants has increased in price. Therefore the need for research on smart scales with components that have relatively cheaper prices. In this study, researchers used the ESP32-CAM microcontroller, which is priced relatively cheaper than the Raspberry Pi 3 Model B. This research still uses the Convolutional Neural Network (CNN) method and a load cell equipped with the HX711 module as a sensor to obtain the weight value of an object. The dataset collected totaled 600 image data with 150 image data for each type of vegetable, classes in the training data consisted of tomatoes, cabbage, carrots, and potatoes. Smart scales using the ESP32-CAM get results of a classification accuracy of 90% and the average difference of the tools built is 0.8 grams compared to the SF-400 brand digital scales.
Komparasi Algoritma Naïve Bayes Dan Support Vector Machine (SVM) Pada Analisis Sentimen Spotify Ayu Sri Rahayu; Ahmad Fauzi; Rahmat Rahmat
Jurnal Sistem Komputer dan Informatika (JSON) Vol. 4 No. 2 (2022): Desember 2022
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/json.v4i2.5398

Abstract

The Spotify app is a subject of interest to social networking communities with significant disagreements or sentiments. Sentiment Analysis is a solution to automatically categorize opinions or ratings into negative or positive opinions. The techniques used in this research are Support Vector Machines (SVM) and Naïve Baye. The advantages of Naïve Bayes are simple, fast and high accuracy. SVM, on the other hand, can identify different hyperplanes that maximize the margin between two different classes. The classification results of this study have two category labels, namely negative and positive. The resulting accuracy value indicates the best test model for sentiment classification cases. Accuracy is measured by the confusion matrix and the results show that the accuracy value of the SVM algorithm is 84% while the accuracy value of the Naïve Bayes algorithm is higher than SVM which is 86.4%.
Model Machine Learning Untuk Analisis Sentimen Masyarakat Terhadap Kenaikan PPN di Media Sosial X Ilham Ridho Pratama; Yana Cahyana; Rahmat Rahmat; Deden Wahiddin
Bulletin of Computer Science Research Vol. 5 No. 4 (2025): June 2025
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bulletincsr.v5i4.523

Abstract

This study examines people's reactions to the Indonesian government's plan to adjust the VAT rate from 11% to 12%, which is scheduled to take effect in 2025. This policy triggered a variety of opinions among netizens, especially on the social networking service X. To explore public opinion, data was collected through web crawling techniques from October to December 2024, resulting in 1,871 records. Then the dataset was preprocessed by text cleaning, case folding, tokenization, stopword removal, and stemming, and the dataset was reduced to 1806. In addition, up to 1000 data will be manually labeled, negative, neutral, positive, by language experts to ensure that each sentence has the appropriate label. These data are used for testing and training, then up to 806 unlabeled data are used as final testing. At the word weighting stage, the Term Frequency-Inverse Document Frequency (TF-IDF) method is used to perform the process. In this study, three machine learning algorithms were used to compare the classification performance, namely Support Vector Machine (SVM), Random Forest, and Decision Tree. Based on the evaluation results, the SVM algorithm recorded the highest accuracy rate of 94%, followed by Random Forest with 93% and Decision Tree with 91%. The results showed a predominance of negative sentiments, indicating public dissatisfaction with the policy. This study proves that machine learning techniques can be effectively used to capture public perceptions through social media, which in turn can be a benchmark for the government to make decisions that will be enforced.
Analisis Sentimen Masyarakat Terhadap Pembatasan BBM Pertalite Menggunakan Random Forest dan K-Nearest Neighbor Farhan Muhammad Fadillah; Yana Cahyana; Rahmat Rahmat; Ahmad Fauzi
Bulletin of Computer Science Research Vol. 5 No. 4 (2025): June 2025
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bulletincsr.v5i4.547

Abstract

This study aims to analyze public opinion regarding the policy of limiting the use of Pertalite fuel by examining user comments on the Instagram platform. To classify these opinions, classification approaches using K-Nearest Neighbor (KNN) and Random Forest algorithms were employed. Comments were categorized into three sentiment expressions: positive, negative, and neutral. The research stages included data collection (crawling), text cleaning and normalization, sentiment labeling, weighting using the TF-IDF technique, model development, and performance evaluation. A total of 2,081 comments were used, with 1,000 comments labeled by language experts as training data, and the remaining used for testing. Model evaluation was conducted using two data splitting ratios, 80:20 and 70:30, to assess classification stability and accuracy. The results indicate that the Random Forest algorithm consistently outperforms KNN, achieving the highest accuracy of 73% under the 80:20 scenario. The classification distribution suggests a dominance of negative sentiment in public opinion toward the policy. These findings reflect public dissatisfaction and serve as critical input for the government in reviewing the subsidized fuel distribution policy. This research also highlights the potential of social media as an alternative data source for real-time public perception analysis.
Co-Authors Ahmad Fauzi Ayu Sri Rahayu Deden Wahiddin Farhan Muhammad Fadillah Hanung Pangestu Rahman Ilham Ridho Pratama Indra, Jamaludin Yana Cahyana