Garuda - Garba Rujukan Digital

Analisis Sentimen Ulasan Pelanggan Terhadap Layanan ERHA-Clinic Berbasis NLP Menggunakan Algoritma SVM Antika, Azizah Qolbu; Agustina, Nova; Wijayati, Diyah
Eksplora Informatika Vol 14 No 2 (2025): Jurnal Eksplora Informatika
Publisher : Institut Teknologi dan Bisnis STIKOM Bali

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30864/eksplora.v14i1.1273

Ulasan pelanggan adalah indikator penting dalam menilai kualitas layanan di suatu klinik kecantikan. Di era digital, ulasan pelanggan tersebar luas di berbagai platform media sosial. Oleh karena itu, penting untuk memahami sentimen dan opini pelanggan terhadap layanan yang diberikan. Mengelola ulasan pelanggan secara manual menjadi tidak efisien dan memakan waktu, terutama dengan volume ulasan yang terus meningkat. Dengan memanfaatkan teknologi seperti Natural Language Processing (NLP) dan algoritma Machine Learning, Support Vector Machine (SVM), proses analisis sentimen menjadi lebih cepat dan efisien. Penelitian ini bertujuan untuk mengembangkan sistem yang mengumpulkan ulasan dari berbagai platform media sosial seperti Instagram, TikTok, dan Google Review, serta menganalisis sentimen menggunakan teknologi NLP dan algoritma SVM. Metode penelitian ini bersifat kuantitatif, dan untuk metode pengembangan sistem, penelitian ini menggunakan Machine Learning Life Cycle. Hasil uji algoritma SVM dalam penelitian ini menunjukkan bahwa Kernel RBF dan Kernel Linear memiliki akurasi masing-masing sebesar 90% dan 92%, yang mengindikasikan bahwa model SVM dengan Kernel Linear memberikan kinerja yang lebih stabil dan andal dibandingkan dengan Kernel RBF.

Pendekatan Ensemble untuk Analisis Sentimen Covid19 Menggunakan Pengklasifikasi Soft Voting Agustina, Nova; Ihsan, Candra Nur
Jurnal Teknologi Informasi dan Ilmu Komputer Vol 10 No 2: April 2023
Publisher : Fakultas Ilmu Komputer, Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25126/jtiik.20236215

Covid19 berdampak pada sektor kehidupan, mulai dari sektor ekonomi, pendidikan, kesehatan, invertasi, pariwisata hingga menimbulkan krisis lain yaitu fenomena ketakutan dan kepanikan masyarakat yang dipicu oleh informasi yang tidak lengkap dan akurat. Ketakutan dan kepanikan massa menyebabkan publik mempublikasikan sentimen di media sosial untuk memberikan tanggapan atau kritik terhadap keputusan yang dibuat oleh negara. Pandangan masyarakat terhadap Covid19 perlu dijadikan landasan sebagai pendukung keputusan untuk menyusun kebijakan pemerintah dalam menangani Covid19 di Indonesia. Penelitian ini bertujuan untuk membandingkan dan menerapkan algoritma Logistic Regression, Naïve Bayes, dan Support Vector Machine menggunakan pengklasifikasi dari ensemble, yaitu Soft Voting untuk analisis sentimen perihal Covid19 pada media sosial Twitter. Implementasi Soft Voting untuk analisis sentiment masyarakat Indonesia terhadap Covid19 menjadi kebaruan pada penelitian ini. Soft Voting akan menentukan prediksi baru berdasarkan rekomendasi maksimum dari berbagai model yang diperlukan untuk analisis sentimen. Pada penelitian ini, semua algoritma mendapatkan akurasi yang sama untuk analisis sentimen, yaitu sebesar 89%. Penerapan metode ensemble meningkatkan akurasi model untuk prediksi sentimen menjadi 91%.Abstract Covid-19 has impacted all sectors of life, ranging from the economic sector, education, health, investment, tourism to causing another crisis, i.e., the phenomenon of public fear and panic triggered by incomplete and accurate information. Fear and panic cause the public to publish sentiments on social media to provide feedback or criticism of decisions made by the state. The public's view of Covid-19 needs to be used as a basis for decision support to formulate government policies in dealing with Covid-19 in Indonesia. This study aims to compare and apply the Logistic Regression, Naïve Bayes, and Support Vector Machine algorithms using the classifier from ensemble, i.e., Soft Voting for sentiment analysis related to Covid19 on Twitter social media. The application of Soft Voting for the analysis of Indonesian public's sentiments towards Covid19 is a novelty in this research. Soft Voting will determine new predictions based on maximum recommendations from various models needed for sentiment analysis. In this study, all algorithms get the same accuracy for sentiment analysis, which is 89%. The application of the ensemble method increases the accuracy of the model for sentiment prediction by up to 91%.

Analisis Sentimen Ulasan Pelanggan Terhadap Layanan ERHA-Clinic Berbasis NLP Menggunakan Algoritma SVM Antika, Azizah Qolbu; Agustina, Nova; Wijayati, Diyah
Eksplora Informatika Vol 14 No 2 (2025): Jurnal Eksplora Informatika
Publisher : Institut Teknologi dan Bisnis STIKOM Bali

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30864/eksplora.v14i1.1273

Ulasan pelanggan adalah indikator penting dalam menilai kualitas layanan di suatu klinik kecantikan. Di era digital, ulasan pelanggan tersebar luas di berbagai platform media sosial. Oleh karena itu, penting untuk memahami sentimen dan opini pelanggan terhadap layanan yang diberikan. Mengelola ulasan pelanggan secara manual menjadi tidak efisien dan memakan waktu, terutama dengan volume ulasan yang terus meningkat. Dengan memanfaatkan teknologi seperti Natural Language Processing (NLP) dan algoritma Machine Learning, Support Vector Machine (SVM), proses analisis sentimen menjadi lebih cepat dan efisien. Penelitian ini bertujuan untuk mengembangkan sistem yang mengumpulkan ulasan dari berbagai platform media sosial seperti Instagram, TikTok, dan Google Review, serta menganalisis sentimen menggunakan teknologi NLP dan algoritma SVM. Metode penelitian ini bersifat kuantitatif, dan untuk metode pengembangan sistem, penelitian ini menggunakan Machine Learning Life Cycle. Hasil uji algoritma SVM dalam penelitian ini menunjukkan bahwa Kernel RBF dan Kernel Linear memiliki akurasi masing-masing sebesar 90% dan 92%, yang mengindikasikan bahwa model SVM dengan Kernel Linear memberikan kinerja yang lebih stabil dan andal dibandingkan dengan Kernel RBF.

Neural Dynamic Network for Brain Tumor Classification: An Attention-Based Feature Selection Approach Naseer, Muchammad; Agustina, Nova; Gusdevi, Harya; Riyanti, Niken
CogITo Smart Journal Vol. 11 No. 2 (2025): Cogito Smart Journal
Publisher : Fakultas Ilmu Komputer, Universitas Klabat

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31154/cogito.v11i2.989.430-446

Magnetic Resonance Imaging (MRI) plays a vital role in the early detection of brain tumors. However, standard Convolutional Neural Network (CNN) models often struggle to extract truly relevant features from complex MRI structures. This limitation creates a gap in achieving robust and clinically interpretable classifications, as feature redundancy and weak attention toward tumor-specific regions may reduce diagnostic reliability. To address this gap, this study introduces a Neural Dynamic Network (NDN) that integrates EfficientNetV2S with a dynamic attention-based mechanism to adaptively highlight informative features while suppressing noise. The proposed model was evaluated using a 5-fold cross-validation scheme and tested on unseen data. Compared with the baseline CNN, the NDN consistently demonstrated higher accuracy, precision, recall, and F1-score across folds and final testing, reflecting improved robustness and balanced sensitivity. NDN yielded significant improvements, with the 5-fold validation averaging an accuracy of 88.44%, a precision of 87.84%, a recall of 87.88%, and an F1-score of 87.82%. Beyond numerical performance, interpretability analysis utilizing Grad-CAM demonstrated that NDN generates more concentrated and clinically consistent heatmaps. In contrast, the baseline CNN produced dispersed activations that exhibited less alignment with tumor regions. Overall, the findings confirm that incorporating a dynamic attention-based mechanism substantially enhances both feature selection and visual interpretability. This makes the NDN architecture more reliable for MRI-based brain tumor classification and highly suitable as a decision-support tool in clinical workflows.

Digital Sovereignty and The Right to Data: A Comparative Study Between Indonesia, The European Union, and The United States Rahayudin, Rahayudin; Naseer, Muchammad; Agustina, Nova; Guterres, Antonio
Journal of Law and Social Politics Vol. 3 No. 2 (2025): Journal of Law and Social Politics
Publisher : Politeknik Siber Cerdika Internasional

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59261/jlsp.v3i2.71

Background: The rapid expansion of the global digital economy has intensified the importance of regulating data governance, particularly in relation to digital sovereignty and the protection of personal data. However, significant differences persist among national legal frameworks, creating regulatory gaps in cross-border data governance and oversight mechanisms. This condition raises critical legal and policy challenges, especially for developing countries such as Indonesia. Objective: This study aims to analyze and compare the principles of digital sovereignty and the right to personal data in Indonesia, the European Union, and the United States, as well as to assess their legal implications for national policy formulation in each jurisdiction. Methods: This research employs a descriptive qualitative approach using a comparative juridical method. A statutory approach is applied to examine relevant laws and regulations, a comparative approach is used to analyze differences in data governance frameworks across jurisdictions, and a conceptual approach is employed to explore theoretical perspectives on digital sovereignty and data rights. Results: The findings indicate that Indonesia emphasizes state control over data and the obligations of electronic system operators, the European Union prioritizes comprehensive protection of data subjects’ rights through the General Data Protection Regulation, while the United States adopts flexible, sectoral regulations oriented toward private sector innovation. These differing paradigms result in variations in oversight effectiveness, levels of data protection, and cross-border data transfer mechanisms. Conclusion: This study highlights the urgency for Indonesia to strengthen regulatory harmonization, enhance institutional oversight capacity, and develop equitable cross-border data transfer mechanisms in order to reinforce digital sovereignty while aligning with international data protection standards.

Title

Found 15 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 15 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 15 Documents
Search