Journal of Computing and Informatics Research

Sistem Pendukung Keputusan Dalam Pemilihan Siswa-Siswi Berprestasi Menerapkan Metode SAW (Simple Additive Weighting)

2026-04-03T16:20:50+00:00

In facing the development of the era and the era of technology that is developing rapidly at all times, the development of human resources is a top priority in national development, the position and position of students, have a very important role in the teaching and learning activities of students in order to improve student learning achievements in academic and non-academic fields, one of the things that motivates students to always develop themselves is to give an award as an outstanding student with the criteria that have been determined by the school. Temporary observations at Mustafa Private Vocational School in determining outstanding students are carried out manually. This method is considered still less effective and efficient. Based on this, a model for determining outstanding students is needed at Mustafa Private Vocational School with a more efficient and effective system. This system is designed using a decision support system through the Simple Additive Weighting (SAW) method. This system can display the ranking results of outstanding students based on the results of the SAW method calculations.

Sistem Pendukung Keputusan Pemilihan Hotel Terbaik Menggunakan Metode WASPAS dan Pembobotan ROC

2026-04-03T16:14:40+00:00

Choosing the best hotel is often a challenge for travelers because many criteria must be considered such as price, facilities, location, and services. To overcome these problems, this study developed a decision support system (DSS) using Weighted Aggregate Product Sum Assessment (WASPAS) and Rank Order Central Weighting (ROC).The WASPAS method was chosen because it has the ability to combine the advantages of the weighted sum model (WSM) and the weighted product model (WPM), resulting in a more accurate and efficient decision.While the ROC method is used to determine the weight of each criterion objectively based on the importance of these criteria. From the calculation results, Hotel C ranks highest with a value of 0.877, indicating that this hotel meets the predetermined criteria better than other alternatives. In addition, other hotels such as Hotel A and Hotel D also performed quite well, occupying the second and third positions.

Analisis Perbandingan Kemiripan Teks Bahasa Daerah di Indonesia Menggunakan Algoritma Naive Bayes dan K-Nearest Neighbor

2025-11-30T09:44:54+00:00

Indonesia, as an archipelagic country, has a wide variety of languages, with 718 regional languages. However, many regional languages face the risk of declining usage and even extinction. Technological developments have opened up opportunities to analyze the patterns and unique characteristics of regional languages through n-gram analysis using naive bayes and k-nearest neighbor algorithms. Therefore, this study was conducted with the aim of analyzing the similarity of regional languages, particularly Central Javanese, Sundanese, and Pontianak Malay, as part of an effort to assist in the preservation of regional languages in Indonesia. The similarity between languages was calculated based on errors in the confusion matrix, and the performance of the algorithms was evaluated using accuracy and F1-score metrics. The naive bayes algorithm with combined unigram and bigram features showed the best performance with an accuracy and F1-score of 0.921. The results of the study showed the highest similarity value in the ‘Javanese - Malay’ language, although only 3.82%, and the lowest in the ‘Malay - Sundanese’ language at 1.66%. These similarity values are based on the dominant characters that appear in a language, such as ‘e’ in Malay and ‘a’ and ‘u’ in Sundanese. This study proves that there is little similarity between Javanese, Sundanese, and Malay.

Analisis Sentimen Program Mbg Menggunakan Algoritma Random Forest Dan Naive Bayes

2025-12-01T07:27:48+00:00

Abstrak: Transformasi digital telah mendorong perubahan besar dalam berbagai aspek kehidupan, salah satunya melalui kemunculan teknologi MBG yang memunculkan beragam opini publik. Penelitian ini menganalisis 6.728 komentar masyarakat di media sosial X (Twitter) menggunakan pendekatan text mining untuk menilai sentimen terhadap MBG serta membandingkan performa dua algoritma, yaitu Naïve Bayes dan Logistic Regression. Hasil awal menunjukkan akurasi masing-masing sebesar 90% dan 91%, namun ketidakseimbangan data dengan dominasi sentimen positif menurunkan nilai precision, recall, dan F1-Score. Melalui penerapan metode SMOTE untuk mengatasi ketimpangan data, performa kedua algoritma meningkat, dengan Logistic Regression menunjukkan hasil terbaik (akurasi 95%, precision 94%, recall 93%, dan F1-Score 95%). Temuan ini menunjukkan bahwa Logistic Regression lebih unggul dalam menganalisis sentimen masyarakat terhadap perkembangan teknologi MBG.

Kata kunci: Naïve Bayes, Logistic Regression, MBG, Analisis Sentimen.

Abstract: Digital transformation has driven significant changes in various aspects of life, one of which is through the emergence of MBG technology, which has generated diverse public opinions. This research analyzes 6,728 public comments on the social media platform X (Twitter) using a text mining approach to assess sentiment towards the MBG and to compare the performance of two algorithms: Naïve Bayes and Logistic Regression. Initial results showed respective accuracies of 90% and 91%, but data imbalance, with a dominance of positive sentiment, lowered the precision, recall, and F1-Score values. Through the application of the SMOTE method to address the data imbalance, the performance of both algorithms improved, with Logistic Regression showing the best results (95% accuracy, 94% precision, 93% recall, and 95% F1-Score). These findings indicate that Logistic Regression is superior in analyzing public sentiment towards the development of MBG technology.

Keywords: Naïve Bayes, Logistic Regression, MBG, Sentiment Analysis.

Implementasi MinIO Sebagai Storage dalam Aplikasi LMS Guru Berbasis Docker

2025-12-01T09:01:05+00:00

Abstrak− Pengelolaan file dan data dalam sistem manajemen pembelajaran (LMS) menjadi salah satu tantangan besar dalam pengembangan aplikasi berbasis cloud. Salah satu solusi penyimpanan yang efisien adalah menggunakan MinIO sebagai penyimpanan objek terdistribusi, yang diintegrasikan dengan teknologi container Docker. Penelitian ini bertujuan untuk mengimplementasikan MinIO sebagai storage dalam aplikasi LMS yang dapat dikelola secara efisien dan skalabel. Metode yang digunakan adalah pengembangan aplikasi berbasis Docker, dengan MinIO sebagai komponen penyimpanan data. Hasil yang diperoleh menunjukkan bahwa penggunaan MinIO dalam lingkungan Docker memberikan kinerja yang optimal dalam hal pengelolaan file, kecepatan akses data, serta kemudahan dalam pengelolaan penyimpanan terdistribusi. Sistem ini berhasil diterapkan dalam LMS Guru, yang memungkinkan pengelolaan file pembelajaran dengan kategori, upload/download, serta dashboard monitoring yang intuitif. Penelitian ini menyimpulkan bahwa integrasi MinIO dan Docker dapat memberikan solusi efektif untuk pengelolaan data pada aplikasi LMS berbasis cloud.

Kata Kunci: MinIO; Docker; Penyimpanan Terdistribusi; LMS; Aplikasi Cloud

Analisis Sentimen Kebijakan Penempatan Dana 200T Di Bank Bumn Menggunakan Algoritma Support Vector Machine

2025-12-16T19:32:03+00:00

The policy of placing Rp200 trillion in state-owned banks (BUMN) has sparked extensive debate and elicited diverse public reactions. Frequently discussed issues include the transparency of the policy, potential risks to the national budget, and the role of the banking sector in strengthening liquidity and supporting economic recovery. Timely insights into public reception are essential so that government communication strategies and risk-mitigation measures can be better targeted. This study aims to map the direction of public sentiment, identify the most salient topics, and evaluate the extent to which computational classification approaches can be used to monitor opinions on an ongoing basis. The findings indicate clear polarization between support and criticism. Negative discussions typically emphasize accountability, governance, and concerns over fiscal risk, while positive discussions highlight the policy’s potential benefits for liquidity, smoother credit distribution, and overall economic stability. These results provide an empirical basis for government and industry stakeholders to sharpen key messages, clarify mechanisms and oversight processes, and anticipate issues that could lead to misinformation. In addition, sentiment monitoring can be conducted periodically as an early-warning system to detect shifts in public perceptions toward similar policies in the future.