Claim Missing Document
Check
Articles

Found 22 Documents
Search

Sentiment Analysis of Rohingya Refugees in Aceh using Support Vector Machine (SVM) and Multinomial Logistic Regression Baliputra, Gigih Army Buana; Kacung, Slamet; Santoso, Budi
Sistemasi: Jurnal Sistem Informasi Vol 14, No 3 (2025): Sistemasi: Jurnal Sistem Informasi
Publisher : Program Studi Sistem Informasi Fakultas Teknik dan Ilmu Komputer

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32520/stmsi.v14i3.5159

Abstract

The rapid development of information technology affects the massive dissemination of information. Social media is one of them, and it contributes to communication and information technology. Information about Rohingya ethnic refugees in Aceh has spread widely on social media. This research aims to analyze public sentiment regarding ethnic Rohingya refugees in Aceh on X and YouTube, categorized into positive, neutral, and negative. This study aims to develop an application that uses the Support Vector Machine (SVM) and Multinomial Logistic Regression techniques to conduct sentiment analysis on public opinion with positive, neutral, and negative classifications regarding Rohingya refugees in Aceh. The 3683 comments collected through web crawling were categorized into positive, negative, and neutral sentiments. The analysis results show that 2112 data were classified as negative sentiments, 1400 as neutral sentiments, and 171 as positive sentiments. Based on the test results, the SVM and Multinomial Logistic Regression methods have similar accuracy of 83.18%. However the SVM method obtained 74.65% precision and 65.15% recall. Meanwhile, the Multinomial Logistic Regression method obtained 75.28% precision and 66.84% recall.
Sistem Pendukung Keputusan Seleksi Pemilihan Pemain Tim Futsal Menggunakan Metode ROC dan ARAS Yusuf, Adrian Edoardo; Santoso, Budi; Kacung, Slamet
Journal of Information System Research (JOSH) Vol 5 No 4 (2024): Juli 2024
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josh.v5i4.5457

Abstract

Futsal's popularity remains undiminished, captivating communities, including school environments like SMK Unitomo Surabaya. In this school, building a strong futsal team is the cornerstone of achieving success. However, manual player selection processes often encounter obstacles, such as inefficiency and potential subjectivity. Often, coaches do not record selection results, leading them to evaluate selections subjectively.Therefore, this research presents a solution in the form of a Decision Support System (DSS) to assist coaches in identifying potential core futsal players. This DSS integrates two cutting-edge methods: Rank Order Centroid (ROC) and Additive Ratio Assessment (ARAS). The ROC method plays a role in data weighting, assigning measurable values to each selection criterion. On the other hand, ARAS plays a role in determining the best alternative by comparing the overall value of each alternative with the optimal value of the entire series. Research results demonstrate that this DSS can generate rankings of potential core futsal players with an accuracy level of 0.8753324. This indicates that this DSS has great potential to assist coaches in selecting the right players and increasing the team's chances of winning.