Article Per Year (5 Year)
p-Index From 2021 - 2026
2.907
P-Index
This Author published in this journals
All Journal Information Management For Educators And Professionals (IMBI) METHODIKA: Jurnal Teknik Informatika dan Sistem Informasi Jurnal Informasi dan Komputer Jurnal Informatika dan Rekayasa Elektronik JURSIMA (Jurnal Sistem Informasi dan Manajemen) Jurnal Ilmu Komputer dan Teknologi (IKOMTI) Prosiding Seminar Nasional Sisfotek (Sistem Informasi dan Teknologi Informasi) PROSISKO : Jurnal Pengembangan Riset dan observasi Rekayasa Sistem Komputer Journal of Artificial Intelligence and Engineering Applications (JAIEA) Jurnal Teknik Mesin, Industri, Elektro dan Informatika JURSIMA Jurnal Nasional Teknik Industri, Sistem Informasi dan Teknik Informatika
Ade Irma Purnamasari
Unknown Affiliation
Automotive Engineering Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Education Electrical & Electronics Engineering Engineering Industrial & Manufacturing Engineering Library & Information Science Mathematics Mechanical Engineering Social Sciences Other

Published : 17 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 17 Documents
Search

 1   2 
Sentiment analysis to classify TikTok Shop Users on Twitter with Naïve Bayes Classifier Algorithm Lestari, Ayu; Ade Irma Purnamasari; Agus Bahtiar; Edi Tohidi
Journal of Artificial Intelligence and Engineering Applications (JAIEA) Vol. 4 No. 2 (2025): February 2025
Publisher : Yayasan Kita Menulis

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59934/jaiea.v4i2.748

Abstract

Advances in information technology have facilitated the use of social media as an e-commerce platform, with TikTok Shop enabling in-person transactions. This research addresses the gap in understanding user perceptions of TikTok Shop through sentiment analysis on Twitter. Sentiment classification is performed using the Naïve Bayes Classifier algorithm. The dataset consists of 1,907 Indonesian tweets, collected from January 2023 to July 2024, and processed using RapidMiner in the Knowledge Discovery in Database (KDD) framework. The preprocessing stages include data cleaning, normalization, tokenization, stopword removal, and stemming. To overcome data imbalance, Synthetic Minority Oversampling Technique (SMOTE) was applied. The model achieved 93.98% accuracy, with balanced precision and recall for positive, neutral, and negative sentiments. The sentiment distribution among TikTok Shop users on Twitter was 35.5% positive, 35.5% negative, and 29.0% neutral. This research provides insights into consumer behavior on social media and emphasizes the importance of sentiment analysis to increase user engagement and understand market perception. This research is expected to provide information to platform developers and businesses looking to improve TikTok
K-Means Algorithm for Grouping Models of Dengue Fever Prone Areas in Cirebon City Aida Safitri; Ade Irma Purnamasari; Agus Bahtiar; Edi Tohidi
Journal of Artificial Intelligence and Engineering Applications (JAIEA) Vol. 4 No. 2 (2025): February 2025
Publisher : Yayasan Kita Menulis

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59934/jaiea.v4i2.834

Abstract

Dengue hemorrhagic fever (DHF) is an infectious disease transmitted through the Aedes aegypti mosquito. DHF cases in Cirebon City show a significant increase every year. This study aims to classify dengue prone areas based on case data per health center in 2020-2024 obtained from the Cirebon City Health Office. The method used is the K-Means algorithm with the Knowledge Discovery in Database (KDD) approach, which includes data selection, preprocessing, data transformation, data mining, evaluation, and knowledge. Evaluation using Davies-Bouldin Index (DBI) showed optimal results at k = 6 with a DBI value of -0.445. The clustering results produced six clusters: cluster 5 (437 dengue cases in 34 health centers) showed high risk; cluster 0 (244 cases), cluster 2 (129 cases), and cluster 3 (279 cases) showed medium risk; while cluster 1 (69 cases) and cluster 4 (86 cases) showed low risk. This study shows that the K-Means algorithm is effective in identifying DHF risk distribution patterns and provides a strategic basis for the Cirebon City Health Office to prioritize interventions and develop more effective prevention strategies.
PENINGKATAN MODEL KLASIFIKASI SENTIMEN PENGGUNA APLIKASI TOMORO COFFEE MENGGUNAKAN ALGORITMA NAÏVE BAYES Dina Audina; Ade Irma Purnamasari; Agus Bahtiar; Edi Tohidi
Jurnal Informatika dan Rekayasa Elektronik Vol. 8 No. 1 (2025): JIRE APRIL 2025
Publisher : LPPM STMIK Lombok

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Kemajuan teknologi informasi telah merevolusi cara bisnis berinteraksi dengan pelanggan melalui aplikasi mobile, termasuk dalam sektor makanan dan minuman. Aplikasi Tomoro Coffee menghadapi tantangan dalam mempertahankan kepuasan pengguna akibat keterbatasan fitur dan masalah teknis. Penelitian ini bertujuan untuk menerapkan algoritma Naïve Bayes guna meningkatkan model klasifikasi sentimen ulasan pengguna, menganalisis distribusi sentimen positif dan negatif beserta faktor utama yang memengaruhinya, serta mengevaluasi performa model berdasarkan akurasi, presisi, recall, dan F1-score. Data ulasan dikumpulkan dari Google Play Store dan diolah menggunakan metode Knowledge Discovery in Database (KDD), yang mencakup pembersihan data, tokenisasi, penghapusan stopword, stemming, serta ekstraksi fitur menggunakan Term Frequency-Inverse Document Frequency (TF-IDF). Hasil penelitian menunjukkan bahwa algoritma Naïve Bayes mencapai akurasi sebesar 90%, dengan presisi 91,3%, recall 87,3%, dan F1-score 88,7%. Temuan ini memberikan wawasan strategis bagi pengembang aplikasi dalam meningkatkan layanan dan fitur berdasarkan analisis sentimen pengguna. Dari hasil analisis, 64,4% ulasan tergolong positif, didominasi oleh komentar seperti "kopinya enak", sementara 35,6% ulasan negatif umumnya berisi keluhan teknis, seperti "tidak tersedia".
Clustering Analysis of Administrative Service Types Using K-Means (Study Case: Village bojongsalam) Wafiq Azizah; Ade Irma Purnamasari; Agus Bahtiar; Kaslani
Journal of Artificial Intelligence and Engineering Applications (JAIEA) Vol. 4 No. 2 (2025): February 2025
Publisher : Yayasan Kita Menulis

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59934/jaiea.v4i2.867

Abstract

Advances in information technology present significant opportunities for the improvement of public services, especially in relation to the administrative functions of Bojongsalam Village. Reliance on traditional methods often leads to inefficiencies and inaccuracies in administrative processes. This research uses the K-Means algorithm to categorize administrative service data based on service type, document number, printing date, and accompanying remarks. Utilizing the Knowledge Discovery in Databases (KDD) framework, the analysis includes data selection, pre-processing, transformation, and clustering analysis conducted through RapidMiner software. The dataset consisted of 718 administrative records that had undergone a rigorous cleaning process, including attribute normalization. The analysis resulted in an optimal Davies-Bouldin Index (DBI) value of -0.498 at K = 4, with each cluster representing a different service utilization pattern. The issuance of Family Cards (KK) and Birth Certificates showed higher demand compared to other available services. This classification promotes workload optimization, fair resource allocation, and formulation of effective operational strategies. The application of the K-Means algorithm demonstrated its effectiveness in data clustering and made a significant contribution to technology-based administrative management. The findings lay a basic framework for addressing the needs of the community in a timely manner.
Analisis Peramalan Tingkat Pengangguran Terbuka di Jawa Barat: Pendekatan Time Series menggunakan Metode ARIMA Adi Pangestu; Ade Irma Purnamasari; Irfan Ali
Jurnal IT UHB Vol 5 No 1 (2024): Jurnal Ilmu Komputer dan Teknologi
Publisher : Universitas Harapan Bangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35960/ikomti.v5i1.1298

Abstract

Tingkat pengangguran menjadi indikator penting dalam mengukur stabilitas ekonomi suatu daerah. Penelitian ini membahas tentang analisis model dan peramalan tingkat pengangguran terbuka di Wilayah Jawa Barat menggunakan metode ARIMA (Autoregressive Integrated Moving Average). Penelitian ini menggunakan data deret waktu (time-series) 6 bulanan tingkat pengangguran terbuka dari tahun 2007 hingga 2023 yang bersumber dari Badan Pusat Statistik, Opendatajabar dan Dinas Ketenagakerjaan Provinsi Jawa Barat. Analisis dimulai dengan identifikasi model ARIMA, estimasi parameter, cek diagnostik, evaluasi model dan peramalan. Peramalan dilakukan untuk 3 tahun ke depan (2024 - 2026). Model ARIMA(1,0,0) dipilih berdasarkan evaluasi parameter seperti Root Mean Squared Error(RMSE), Mean Absolute Error(MAE) dan Mean Abs Percent Error(MAPE). Hasil peramalan menunjukkan peningkatan tingkat pengangguran pada Februari 2024 7,92% menjadi 8,40% pada Agustus 2026. Hasil menunjukkan pola tren naik yang berkelanjutan. Peningkatan tingkat pengangguran di Wilayah Jawa Barat dipengaruhi oleh faktor kebijakan ekonomi, struktur industri, dinamika teknologi, dan pendidikan. Peran pemerintah dalam menciptakan lapangan kerja, reformasi pendidikan, dan kebijakan investasi menjadi krusial dalam menanggulangi masalah ini. Penelitian ini memberikan kontribusi dalam pemahaman dan peramalan tingkat pengangguran terbuka di Wilayah Jawa Barat. Model ARIMA(1,0,0) dapat digunakan sebagai alat yang efektif untuk meramalkan perubahan tingkat pengangguran di masa mendatang. Oleh karena itu, perumusan kebijakan yang mendukung pertumbuhan ekonomi dan penciptaan lapangan kerja diperlukan untuk mengatasi tantangan ini.
Arsitektur Ensemble Convolutional Neural Network untuk Klasifikasi Multi Kelas Penyakit Daun Kopi Ade Irma Purnamasari; Dadang Sudrajat; Yudhistira Arie Wijaya
Prosiding SISFOTEK Vol 9 No 1 (2025): SISFOTEK IX 2025
Publisher : Ikatan Ahli Informatika Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Coffee leaf disease remains one of the most significant threats to global coffee production, particularly Coffee Leaf Rust (CLR) caused by Hemileia vastatrix. Early and accurate disease detection is essential for maintaining yield stability and ensuring sustainable coffee farming. This study proposes an Ensemble Convolutional Neural Network (CNN) architecture that combines MobileNetV2 and ResNet50 to enhance robustness and generalization in multi-class classification of coffee leaf diseases. The dataset consists of 1,664 images categorized into four classes: miner, nodisease, phoma, and rust, collected from both public repositories and real-field observations. Image preprocessing includes resizing, normalization, and augmentation to increase diversity and reduce overfitting. The ensemble model is trained using the Adam optimizer with a learning rate of 0.0001 and evaluated through accuracy, precision, recall, and F1-score metrics. Results demonstrate that the ensemble CNN outperforms single CNN architectures, achieving an accuracy of 95.6%, precision of 94.4%, and F1-score of 94.2%, even under challenging illumination and noise conditions. Compared to individual models, performance improvement ranges from 2%–4%. The model also maintains higher stability when tested under low-light and noisy images, confirming its robustness in real-world scenarios. This study concludes that ensemble CNN offers a reliable and efficient framework for real-time coffee leaf disease detection and can serve as a foundation for developing intelligent agricultural systems using edge computing.
ALGORITMA RANDOM FOREST UNTUK PREDIKSI STATUS PINJAMAN BERDASARKAN SKOR KREDIT Attaufiqqurrohman, Hadit; Ade Irma Purnamasari; Denni Pratama; Nining Rahaningsih; Willy Prihartono
METHODIKA: Jurnal Teknik Informatika dan Sistem Informasi Vol. 12 No. 1 (2026): Volume 12 Nomor 1 Tahun 2026
Publisher : Universitas Methodist Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

The rapid development of financial technology has encouraged financial institutions to adopt data-driven credit scoring systems in order to minimize the risk of default. However, many loan eligibility prediction models still face challenges such as data imbalance (class imbalance) and the limited capability of traditional models to capture non-linear relationships among variables. This study aims to develop a loan status prediction model using the Random Forest algorithm combined with the Synthetic Minority Oversampling Technique (SMOTE) and One-Hot Encoding (OHE) to improve model accuracy and generalization capability. The data used in this study are secondary data obtained from the public Kaggle platform, consisting of 45,000 records with 14 demographic and financial attributes. The research method employs a supervised learning approach with several stages, including data acquisition and preprocessing (data cleaning, normalization, encoding, and data balancing), Random Forest model training, and performance evaluation using accuracy, precision, recall, F1-score, and AUC metrics. The results show that the combination of Random Forest, SMOTE, and OHE achieves high predictive performance, with an accuracy of 94.8%, precision of 95.6%, recall of 93.7%, F1-score of 94.6%, and an AUC value of 0.972. The most influential variables in loan status prediction are credit_score, person_income, and loan_amnt. This approach is proven to be effective in addressing data imbalance issues and improving classification accuracy in identifying creditworthy and non-creditworthy borrowers.
Co-Authors Adi Pangestu Agung Prayogo Bagustio agus bahtiar Aida Safitri Aji Santoso Arif Nur Hakim Arif Rinaldi Dikananda Attaufiqqurrohman, Hadit AYU LESTARI Bayu Ryanto Dadang Sudrajat Denni Pratama Dina Audina Edi Tohidi Eka Wisnu Ramadhona Irfan Ali Kaslani Melawati Melawati Mila Sari Moch Feri Izulhaq Nining Rahaningsih Odi Nurdiawan Saeful Anwar Tati Suprapti Teguh Abdi Mangun Tio Prasetya Tri Aditama Wafiq Azizah Willy Prihartono Yudhistira Arie Wijaya