Article Per Year (5 Year)
p-Index From 2020 - 2025
0.444
P-Index
This Author published in this journals
All Journal Jatilima : Jurnal Multimedia Dan Teknologi Informasi Bulletin of Information Technology (BIT)
Sari, Ayu Ofta
Unknown Affiliation
Computer Science & IT

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

 1 
Implementasi Algoritma Naïve Bayes dalam Menganalisis Sentimen Review Pengguna Tokopedia pada Produk Kesehatan Ernawati, Andi; Sari, Ayu Ofta; Sofyan, Siti Nurhaliza; Iqbal, Muhammad; Wijaya, Rian Farta Wijaya
Bulletin of Information Technology (BIT) Vol 4 No 4: Desember 2023
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bit.v4i4.1090

Abstract

It must be realized that customer satisfaction is the main goal for companies in developing their business. Because customers' opinions written on social media will have a big influence on the company and potential customers. In its development, it is increasingly found in various online media, one of which is Tokopedia. Product reviews are an important source of information regarding quality, service and delivery from both consumers and manufacturers. With a very large amount of data for each product on Tokopedia, analyzing and concluding product review information will definitely take a lot of time if done manually. To overcome this, a sentiment analysis system is needed that can automatically extract important information that can objectively determine product quality and handle large amounts of textual information. The sentiment analysis system consists of several stages, namely crawling, pre-processing, word weighting, and sentiment classification. By applying the Naïve Bayes algorithm through selecting range and frequency features, accuracy, accuracy and recall results will be obtained using the Confusion Matrix test. The dataset used is from the kaggle.com site regarding customer sentiment on health products with the type of mask. using the Naïve Bayes Algorithm Method to determine the sentiment of user reviews by classifying 2 positive and negative classes using the NLP approach produces an accuracy value of 88%.
Analisis Faktor Demografi Dan Sosial Ekonomi Untuk Mendeteksi Dini Risiko Putus Kuliah Menggunakan Metode Support Vector Machine (Svm) Dan Decision Tree (Studi Kasus : STMIK Triguna Dharma) Sari, Ayu Ofta; Iqbal , Muhammad; Nasution, Darmeli
Jurnal Multimedia dan Teknologi Informasi (Jatilima) Vol. 7 No. 02 (2025): Jatilima : Jurnal Multimedia Dan Teknologi Informasi
Publisher : Cattleya Darmaya Fortuna

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54209/jatilima.v7i02.1439

Abstract

Fenomena putus kuliah merupakan tantangan serius di perguruan tinggi, termasuk di STMIK Triguna Dharma. Masalah ini dipengaruhi oleh berbagai faktor demografi dan sosial ekonomi, seperti keterbatasan ekonomi keluarga, kurangnya dukungan lingkungan, serta persoalan internal mahasiswa. Penelitian ini bertujuan mengidentifikasi faktor-faktor tersebut dan membangun model prediktif menggunakan pendekatan data mining, khususnya algoritma Support Vector Machine (SVM) dan Decision Tree. Metode yang digunakan adalah kuantitatif. Data diperoleh melalui wawancara dan sistem akademik, kemudian diproses melalui tahapan preprocessing untuk pembersihan dan normalisasi. Algoritma SVM digunakan untuk membangun hyperplane yang memisahkan mahasiswa berisiko dan tidak berisiko putus kuliah, sedangkan Decision Tree menghasilkan model pohon keputusan yang mudah dipahami untuk analisis faktor penyebab. Evaluasi model dilakukan dengan tiga rasio pembagian data: 90:10, 80:20, dan 70:30. Hasil menunjukkan bahwa SVM memiliki akurasi tertinggi sebesar 58,54% dengan presisi 75% dan recall 83,33% pada rasio 90:10. Sementara itu, Decision Tree mencatat recall 100% pada rasio 80:20 dan 70:30, namun dengan presisi lebih rendah (50–57%) dan akurasi maksimum 56,10%. Temuan ini menunjukkan bahwa SVM lebih baik dalam keseimbangan akurasi dan presisi, sedangkan Decision Tree unggul dalam mendeteksi kasus putus kuliah. Model ini diharapkan dapat membantu kampus melakukan intervensi dini untuk mencegah putus kuliah.
Co-Authors Andi Ernawati IQBAL , MUHAMMAD Nasution, Darmeli Sofyan, Siti Nurhaliza Sugeng, Santoso Wijaya, Rian Farta Wijaya