Claim Missing Document
Check
Articles

Found 3 Documents
Search

Implementasi Support Vector Machine untuk Analisis Sentimen Aplikasi Deepseek Prilindaputra, Brilian; Putri, Dinda Rima Rachcita; Ulinnuha, Nurissaidah
INTEGER: Journal of Information Technology Vol 10, No 1 (2025): April
Publisher : Fakultas Teknologi Informasi Institut Teknologi Adhi Tama Surabaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31284/j.integer.2024.v10i1.7541

Abstract

Kemunculan DeepSeek, AI canggih yang dikembangkan di China, telah memberikan dampak yang signifikan terhadap lanskap teknologi global. Namun, pengadopsiannya telah mendapat reaksi beragam, dengan beberapa negara memilih untuk memblokir aksesnya karena masalah keamanan data. Penelitian ini bertujuan untuk menganalisis sentimen pengguna terhadap aplikasi DeepSeek di Google Play Store, secara khusus menargetkan ulasan pengguna dari Amerika Serikat. Dengan menggunakan metode klasifikasi Support Vector Machine (SVM), analisis sentimen dilakukan untuk mengkategorikan opini pengguna ke dalam sentimen positif, netral, dan negatif. Dataset yang terdiri dari 10.000 ulasan yang dikumpulkan melalui web scraping, telah dipreproses menggunakan teknik pembersihan teks, pembobotan TF-IDF, dan lemmatization. Model SVM dilatih dan divalidasi menggunakan k-fold cross validation (k-fold = 10), mencapai akurasi terbaik pada parameter C = 100 dan kernel RBF. Hasil evaluasi menunjukkan akurasi rata-rata 90,33%, dengan akurasi puncak 92,20% pada fold 10. Temuan ini menunjukkan polaritas sentimen yang kuat di antara para pengguna. Penelitian ini penyebaran kata dari analisis wordcloud memberikan wawasan bagi para pengembang dan pemangku kepentingan dalam meningkatkan aplikasi AI dengan mengatasi kekhawatiran pengguna dan meningkatkan kepuasan pengguna secara keseluruhan.
Comparison of Linkage Methods in Hierarchical Clustering for Grouping Districts/Cities in East Java Based on Stunting Determinants Putri, Dinda Rima Rachcita; Ulinnuha, Nurissaidah; Intan, Putroue Kumala
Journal of Applied Informatics and Computing Vol. 9 No. 5 (2025): October 2025
Publisher : Politeknik Negeri Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30871/jaic.v9i5.10919

Abstract

Stunting is a long-term nutritional problem that generally occurs in children under five years old and is characterized by a shorter body than other children of the same age due to continuous dietary deficiencies. As a result of the Indonesian Health Survey (SKI) conducted in 2023, the stunting rate in East Java decreased to 17.7%. In 2024, the target is to reduce it to 14%. This study aims to group regencies and cities in East Java based on indicators of child nutritional status by using five linkage approaches in the hierarchical clustering method. This study found areas with similar causes of stunting so that intervention programs can be more targeted. The analysis showed that the centroid linkage methods formed two clusters with the highest cophenetic correlation coefficient of 0.8619. The first cluster consists of 37 regencies/cities with a low stunting category, and the second cluster consists of one regency/city with a high stunting category. The model in this clustering has a silhouette value of 0.6155, which indicates that the model is in the good category.
Landslide Modeling with the Savage-Hutter Approach Using the Finite Volume Method Prilindaputra, Brilian; Toyibah, Syifa Nasiratun; Putri, Dinda Rima Rachcita; Novitasari , Dian Candra Rini
International Journal of Mechanical Computational and Manufacturing Research Vol. 14 No. 4 (2026): February: Mechanical Computational And Manufacturing Research
Publisher : Trigin Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35335/computational.v14i4.285

Abstract

Landslides are one of the most frequent disasters in Indonesia and have a major impact on the environment and society. This study focuses on modeling the dynamics of landslides in Peniraman Hill, West Kalimantan, using the Savage-Hutter (SH) model solved through the finite volume method (FVM) and the Harten-Lax-van Leer flux scheme. (HLL), supported by the Courant–Friedrichs–Lewy (CFL) method to maintain stable conditions. This study aims to apply the model to real conditions and assess the effectiveness of the numerical approach in describing the movement of land masses. Simulations were conducted on Slopes 1 and 3 which are at risk of landslides due to their soil stability, with three variations of the soil friction angle  to see how changes in these parameters affect the flow mechanism and sliding distance. The results show that the soil friction angle  is a factor that influences landslide behavior. Decreasing the value  makes the landslide move faster and cover a wider area in all parts of the topography. The initial maximum velocity of Slope 1 ranges from ~12–17 m/s with a range of around ~18 meters, while on Slope 3 it reaches ~20–27 m/s with a range of up to ~23.5 meters. Slope 3 consistently produces faster movement and longer sliding distance. Overall, the combination of the SH model with the FVM method and the HLL scheme controlled by CFL conditions has proven to be effective, stable, and capable of representing landslide dynamics. The research results can be an important basis for risk analysis and disaster mitigation strategy planning in the environment around Peniraman Hill to establish exclusion zones and design high load-bearing structures in the potential landslide reach area of ~23.5 meters