Claim Missing Document
Check
Articles

Found 2 Documents
Search

Sentiment Analysis of Free Nutritious Meal Programs Using Naïve Bayes on Platforms X and TikTok Fadila Ullul Azmie; Yudie Irawan; R.Rhoedy Setiawan
Jurnal Teknologi Informasi dan Pendidikan Vol. 19 No. 1 (2026): Jurnal Teknologi Informasi dan Pendidikan
Publisher : Universitas Negeri Padang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24036/jtip.v19i1.1112

Abstract

This study analyzes public sentiment toward the Free Nutritious Meal Program (MBG) using the Multinomial Naive Bayes algorithm on data from X (Twitter) and TikTok. A total of 5,173 entries were collected through web scraping and processed with cleaning, normalization, tokenization, stopword removal, and stemming. To address class imbalance, SMOTE was applied, and evaluation employed accuracy, precision, recall, F1-score, and AUC-ROC. Results show that without SMOTE, the model tended to be biased toward the majority class, especially on TikTok, while after SMOTE recall increased significantly and a better balance between precision and recall was achieved. On Twitter, performance was more stable with a moderate class distribution, and SMOTE further improved sensitivity to positive sentiment. Word cloud analysis revealed differences across platforms: TikTok leaned more toward negative sentiment with dominant words such as “racun,” “korupsi,” and “dapur,” while Twitter showed a stronger balance with positive terms like “gizi,” “gratis,” and “program.” These findings highlight the importance of cross-platform analysis to comprehensively understand public perceptions.
Klasterisasi Kebutuhan Pupuk Bersubsidi Menggunakan Algoritma K-Means dan Elbow Method Nurya Herlina Sari; R.Rhoedy Setiawan; Yudie Irawan
Jurnal Algoritma Vol 23 No 1 (2026): Jurnal Algoritma
Publisher : Institut Teknologi Garut

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33364/algoritma/v.23-1.3361

Abstract

The distribution of subsidized fertilizer at the UD Barokah Tani Kiosk in Pati Regency does not yet meet farmers’ needs due to the manual management of RDKK data. This study aims to cluster subsidized fertilizer needs using the K-Means algorithm, validated by the Elbow Method and Silhouette Score. The data used consists of 1,420 RDKK records for the 2025–2026 period, with variables including land area, UREA_TOTAL, NPK_TOTAL, and the number of commodities. The results indicate that the optimal number of clusters is k = 3, with a Silhouette Score of 0.9192, indicating very high cluster quality. The data is divided into three categories: low, medium, and high, with a dominance in the low to medium categories. This study contributes by comprehensively integrating fertilizer requirement variables and using a combination of the Elbow Method and Silhouette Score to enhance the validity of the clustering results. The clustering results are implemented in a web-based system to support rapid, data-driven analysis and visualization.