Claim Missing Document
Check
Articles

Found 2 Documents
Search

Comparison of Support Vector Machine and K-Nearest Neighbor Algorithms on the Effectiveness of a Free Lunch Program Frenda Farahdinna; Pipit Prabawati
SISTEMASI Vol 15, No 2 (2026): Sistemasi: Jurnal Sistem Informasi
Publisher : Universitas Islam Indragiri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32520/stmsi.v15i2.5999

Abstract

The Free Lunch Program is a government initiative aimed at ensuring adequate nutrition for the public. This study aims to examine public perceptions of the program through sentiment analysis and to compare the effectiveness of Support Vector Machine (SVM) and K-Nearest Neighbor (K-NN) models. A total of 6,532 public comments were collected from Twitter, YouTube, and TikTok. After preprocessing, including normalization, stopword removal, and stemming, features were extracted using Term Frequency–Inverse Document Frequency (TF-IDF), resulting in 5,992 clean data points. The dataset was split into 80% training and 20% testing sets. Model training was conducted with hyperparameter tuning using 3-fold GridSearchCV. The results indicate that negative sentiment dominated at 42.7%. In the model comparison, SVM with a linear kernel significantly outperformed K-NN, achieving an accuracy of 72%, while K-NN (k=3) reached only 48%. These findings suggest that the SVM algorithm is more effective in classifying public opinion sentiment on high-dimensional data compared to K-NN.
Smart Village Smart Governance: Digitalisasi Pengembangan dan Sosialisasi Website Layanan Desa Kademangan.Net Sari Ningsih; Djarot Hindarto; Fauziah Fauziah; Asrul Sani; Endah Tri Esti Handayani; Ratih Titi Komala Sari; Frenda Farahdinna; Erina Rahmazani; Mohammad Aldinugroho Abdullah; Muhammad Mustaqim
Masyarakat Mandiri : Jurnal Pengabdian dan Pembangunan Lokal Vol. 3 No. 2 (2026): April: Masyarakat Mandiri : Jurnal Pengabdian dan Pembangunan Lokal
Publisher : Lembaga Pengembangan Kinerja Dosen

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62951/masyarakatmandiri.v3i2.3085

Abstract

The Community Service Program (PKM) collaboration organized by LLDikti Wilayah III represents a synergistic initiative among higher education institutions to support village digitalization based on the Smart Village Smart Governance concept. The program involved Universitas Nasional as the lead university, in collaboration with Universitas Muhammadiyah Prof. Dr. HAMKA and Institut Transportasi dan Logistik Trisakti as partner institutions, and was implemented in Kademangan Village, Mande District, Cianjur Regency. The activity focused on developing and socializing the Kademangan.net village service website as a digital platform to enhance transparency and efficiency in public services, including access to village information, public complaints, and MSME promotion. The program began with a socialization session at the Village Hall involving village officials and residents, followed by field surveys at the local Posyandu and residents’ homes to identify community needs and preferences regarding digital services. The results indicate that village service digitalization improves accessibility and time efficiency for residents, although assistance is still needed for those less familiar with technology. Overall, this collaborative PKM initiative contributes to strengthening digital-based village governance and serves as a sustainable model of inter-university collaboration in empowering rural communities through information technology.