Garuda - Garba Rujukan Digital

Optimasi Ulasan Pengguna Aplikasi ChatGPT di Google Play Store Menggunakan SMOTE Eka Rahmawati; Candra Agustina
Jurnal Teknologi Informasi dan Terapan Vol 11 No 1 (2024)
Publisher : Jurusan Teknologi Informasi Politeknik Negeri Jember

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25047/jtit.v11i1.360

Artificial Intelligence (AI) menjadi bidang ilmu yang terus dikembangkan dalam berbagai aspek kehidupan. Salah satu aplikasi yang dikembangkan adalah ChatGPT. Aplikasi tersebut memungkinkan adanya interaksi dengan percakapan teks dengan menerapkan model berbasis AI. Terdapat berbagai fitur dan fungsi yang dapat dimanfaatkan oleh pengguna sesuai dengan kebutuhan. Namun, dalam interaksinya terdapat kemampuan yang terbatas dalam pemahaman terhadap konteks yang kompleks dan tingkat akurasi dari teks jawaban yang diberikan. Untuk mengetahui perspektif pengguna aplikasi ChatGPT, maka dapat dilakukan text mining melalui ulasan Google Playstore. Sebelum diolah data yang telah melalui beberapa tahapan pre-processing. Selanjutnya dilakukan klasifikasi dengan implementasi algoritma K-Nearest Neighbors (KNN) dan Deep Learning. Optimasi kinerja algoritma dilakukan dengan Teknik SMOTE. Hasil pengolahan data menunjukan adanya peningkatan akurasi dengan penggunaan SMOTE sebesar 4% pada Deep Learning dan 1,08% pada KNN. Nilai akurasi tertinggi diperoleh dari implementasi SMOTE pada KNN dengan nilai 91,48%.

Clustering-based Machine Learning Approach For Predicting Tourism Trends From Social Media Behavior Candra Agustina; Eka Rahmawati
Jurnal Teknologi Informasi dan Terapan Vol 12 No 1 (2025): June
Publisher : Jurusan Teknologi Informasi Politeknik Negeri Jember

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25047/jtit.v12i1.443

Digital technology has significantly transformed tourist behavior, particularly in searching for, selecting, and sharing travel experiences. Social media has become a primary source of information, influencing travel decisions through real-time recommendations and user-generated content. However, the large volume of data generated by social media presents challenges in understanding and predicting tourist behavior. This study aims to analyze tourist behavior patterns using a clustering-based machine learning approach, specifically K-Means Clustering. The research examines engagement levels on platforms such as Instagram, TikTok, and TripAdvisor to categorize tourists into three key segments: Digital-Savvy Travelers, Passive Travelers, and Conservative Travelers. The results indicate that machine learning effectively analyzes large-scale tourism data, providing valuable insights for destination marketing, personalized recommendations, and service optimization. The findings highlight the potential of machine learning to identify emerging trends, improve customer segmentation, and enhance targeted promotional strategies. Understanding these patterns enables tourism businesses to create data-driven strategies aligned with modern travel behaviors. In a broader perspective, artificial intelligence can revolutionize tourism marketing, increase customer engagement, and improve the overall travel experience

Pemanfaatan Aplikasi SITUBA Sebagai Inovasi Digital Pelaporan Kasus TBC oleh Kader dan Puskesmas di Kelurahan Nusukan Sardiarinto; Supriyanta; Candra Agustina; Wawan Nugroho; Sola Gracia Deo Andrew; Hani Yulia Rachma; Dehant Mahendra H
Jurnal Abdimas Indonesia Vol. 6 No. 1 (2026)
Publisher : Perkumpulan Dosen Muslim Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34697/jai.v6i1.2413

Tuberkulosis (TBC) masih menjadi salah satu masalah kesehatan utama di Indonesia, termasuk di Kota Surakarta. Proses pelaporan kasus TBC di tingkat kelurahan selama ini masih dilakukan secara manual, sehingga sering menimbulkan keterlambatan dalam penyampaian data dan tindak lanjut pasien. Kegiatan pengabdian kepada masyarakat ini bertujuan untuk memperkenalkan dan menerapkan aplikasi digital SITUBA (Sistem Informasi Penanggulangan TBC) sebagai inovasi pelaporan kasus TBC di Kelurahan Nusukan, Kota Surakarta. Kegiatan dilaksanakan oleh tim dosen dan mahasiswa Universitas Bina Sarana Informatika Kampus Surakarta bekerja sama dengan Dinas Kesehatan Kota Surakarta dan Puskesmas Nusukan. Tahapan pelaksanaan meliputi sosialisasi kepada perangkat kelurahan, pelatihan penggunaan aplikasi bagi kader kesehatan, serta pendampingan dalam proses pelaporan kasus secara digital. Hasil kegiatan menunjukkan peningkatan pemahaman dan kemampuan kader dalam menggunakan aplikasi SITUBA untuk mencatat dan melaporkan data pasien secara lebih sistematis. Selain itu, sistem digital ini dinilai membantu mempermudah koordinasi antara kader, kelurahan, dan puskesmas dalam kegiatan pelacakan pasien TBC.Kesimpulannya, penerapan awal aplikasi SITUBA di Kelurahan Nusukan menunjukkan potensi positif dalam mempercepat alur pelaporan dan meningkatkan efisiensi koordinasi lintas pihak dalam upaya penanggulangan TBC berbasis masyarakat.

K-MEANS-BASED TRAINING DATA PROCESSING FOR IMPROVING TOURISM RECOMMENDATION ACCURACY Candra Agustina; Purwanto Purwanto; Farikhin Farikhin; Eka Rahmawati
JITK (Jurnal Ilmu Pengetahuan dan Teknologi Komputer) Vol. 11 No. 4 (2026): JITK Issue May 2026
Publisher : LPPM Nusa Mandiri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33480/jitk.v11i4.7274

This study investigates the enhancement of tourism destination recommendation systems through the use of K-Means clustering to improve training data quality and model accuracy. The rapid advancement of information technology has increased the demand for personalized and accurate recommendation systems within the tourism industry. Despite this, achieving high prediction accuracy remains a significant challenge. This study employs K-Means clustering to segment training data into homogeneous clusters, thereby improving data representation and enhancing the predictive accuracy of recommendation models. The research methodology includes a comprehensive literature review, data collection, preprocessing, clustering, and model testing using K-Nearest Neighbors (KNN), Decision Tree, and Naive Bayes algorithms. The results show that after applying K-Means clustering, KNN's accuracy increased by 2.27%, and its kappa and precision values also improved, indicating enhanced reliability and prediction accuracy. Naive Bayes exhibited substantial improvements with a 9.09% increase in accuracy, alongside significant enhancements in kappa and precision metrics. Conversely, the Decision Tree algorithm experienced a decline in performance after clustering. Therefore, clustering techniques are not suitable for application to the Decision Tree algorithm.

Interpretable Machine Learning for Early Detection of Academically At-Risk Students Using Behavioral, Socio-Demographic and Learning-Related Factors Vadlya Maarif; Eka Rahmawati; Candra Agustina
Telematika Vol 19, No 2: August (2026)
Publisher : Universitas Amikom Purwokerto

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35671/telematika.v19i2.3318

The increasing adoption of learning analytics in higher education has encouraged the development of machine learning models for the early detection of academically at-risk students. However, many predictive models emphasize accuracy while providing limited interpretability for educators and academic advisors. This study proposes an interpretable machine learning framework for predicting academic risk using behavioral, socio-demographic, and learning-related student variables. A publicly available synthetic Kaggle dataset consisting of 500 student records was used as a controlled dataset for methodological validation. The data were preprocessed through missing-value handling, standardization, and one-hot encoding before being divided into training and testing sets. Several classifiers were evaluated, including Naive Bayes, Support Vector Machine, Random Forest, Logistic Regression, and XGBoost. Logistic Regression was employed as an interpretable baseline model, while XGBoost was used as a comparative ensemble classifier. Model performance was evaluated using accuracy, precision, recall, F1-score, AUC, and confusion matrix analysis. The results show that Logistic Regression achieved the highest accuracy and F1-score, with an accuracy of 0.8600 and an F1-score of 0.7812. XGBoost achieved the highest AUC value of 0.9278, followed closely by Logistic Regression with an AUC of 0.9246. Random Forest and XGBoost produced the lowest false negative values, indicating their ability to identify at-risk students more effectively. SHAP-based explainability revealed that weekly study hours, assignment completion, class attendance, and sleep duration were the most influential predictors. These findings suggest that interpretable machine learning can support academic early-warning systems by providing transparent prediction results. Since the dataset is synthetic, the findings should be interpreted as methodological validation rather than direct generalization to real student populations.

Scratch Sebagai Media Stimulasi Kognitif: Penguatan Berpikir Komputasional Berbasis Service Learning pada Pendidikan Dasar Heribertus Ary Setyadi; Wawan Nugroho; Supriyanta Supriyanta; Candra Agustina
WASANA NYATA Vol 10, No 1 (2026)
Publisher : STIE AUB Surakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36587/wasananyata.v10i1.2199

Wacana integrasi kelas pemrograman bagi siswa dasar dan menengah yang diusulkan oleh Wakil Presiden Gibran Rakabuming Raka memicu restrukturisasi kurikulum nasional oleh Kementerian Pendidikan Dasar dan Menengah melalui penyusunan kerangka strategis berbasis coding dan Kecerdasan Buatan (AI). Edukasi pemrograman pada usia dini diproyeksikan mampu menstimulasi penalaran kreatif serta mengonstruksi soft skills abad ke-21 termasuk problem solving, kolaborasi, dan critical thinking, sehingga orientasi siswa bergeser dari konsumen instruksi menjadi arsitek solusi digital. Selaras dengan arah kebijakan tersebut, artikel/kegiatan ini mengkaji program kemitraan bersama Pondok Pesantren dan Panti Asuhan Al Ikhsan Surakarta dalam memitigasi urgensi kesenjangan digital (digital divide) dan keterbatasan logika sistematis siswa. Melalui intervensi teknologis yang terarah, program ini mengombinasikan instruksi teknis dan penguatan psikologis guna memperluas domain kognitif serta membangun efikasi diri siswa. Hasil implementasi menegaskan bahwa sintesis antara metode Service Learning dan platform Scratch efektif mengakselerasi literasi digital serta pertumbuhan kognitif. Transformasi peserta dari pengguna pasif menjadi kreator aktif diindikasikan oleh penguasaan empat pilar Berpikir Komputasional (Computational Thinking): dekomposisi, pengenalan pola, abstraksi, dan perancangan algoritma, yang secara simultan meningkatkan kapabilitas pemecahan masalah secara signifikan.

IMPLEMENTASI ALGORITMA J48 DENGAN TEKNIK BAGGING UNTUK PREDIKSI KIPI PESERTA VAKSINASI COVID-19 Eka Rahmawati; Candra Agustina
Indonesian Journal of Business Intelligence (IJUBI) Vol 5 No 1 (2022): Indonesian Journal of Business Intelligence (IJUBI)
Publisher : Universitas Alma Ata

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21927/ijubi.v5i1.2072

The Covid 19 vaccination is considered to be the most effective way to prevent the spread of the Corona Virus, in addition to a clean lifestyle such as washing hands, wearing masks, and keeping a distance from other people. Several large vaccine manufacturing companies in the world have issued a product in the form of a Covid-19 vaccine with various levels of effectiveness. The vaccine is still being distributed throughout the world, including Indonesia. The vaccine obtained an emergency distribution permit from the authorized institution and was administered to community groups that meet the requirements. However, during the implementation of the vaccine, many AEFIs (Post Immunization Adverse Events) were found, such as dizziness, fever, headaches, and some even fainted. Although not dangerous but quite disturbing for people with solid activities. Therefore, it is necessary to predict whether participants will get AEFI or not. The data consists of 8 Attributes, after being processed using the J48 Algorithm, the results show that the attributes that have a strong influence are 7 Attributes, while the rest have no major effect. The accuracy level of the prediction model obtained is 91,22% with this level of accuracy, it means that the model can be utilized by the parties concerned to then be able to anticipate.

IMPLEMENTASI SMOTE DAN ALGORITMA MACHINE LEARNING UNTUK MENINGKATKAN AKURASI REKOMENDASI HOTEL Candra Agustina; Eka Rahmawati; Denny Irawan; Vriska wahyu Tristanti
Indonesian Journal of Business Intelligence (IJUBI) Vol 7 No 2 (2024): Indonesian Journal of Business Intelligence (IJUBI)
Publisher : Universitas Alma Ata

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21927/ijubi.v7i2.5141

Pariwisata memiliki peran penting dalam perekonomian global, dengan destinasi seperti Candi Borobudur menarik berbagai jenis pengunjung. Untuk meningkatkan pengalaman wisatawan, rekomendasi hotel yang akurat menjadi sangat penting. Namun, data yang tidak seimbang, seperti ulasan positif yang terlalu dominan, sering kali mengurangi kinerja model machine learning yang digunakan untuk rekomendasi. Penelitian ini bertujuan untuk mengatasi masalah tersebut dengan menerapkan Synthetic Minority Over-sampling Technique (SMOTE) guna menyeimbangkan dataset dan meningkatkan akurasi rekomendasi hotel. Beragam algoritma machine learning, termasuk Random Forest, Support Vector Machines, dan Neural Networks, diterapkan dan dievaluasi. Hasil penelitian menunjukkan bahwa penerapan SMOTE secara signifikan meningkatkan kinerja semua model, dengan Random Forest memberikan hasil terbaik. Studi ini menunjukkan bahwa SMOTE, dalam kombinasi dengan teknik machine learning, memberikan solusi yang kuat terhadap ketidakseimbangan kelas pada sistem rekomendasi hotel, sehingga menghasilkan rekomendasi yang lebih andal dan relevan bagi wisatawan. Temuan ini memiliki implikasi penting bagi manajemen hotel dan sektor pariwisata secara keseluruhan.

Develompent of Machine Learning Model to Predict Hotel Room Reservation Cancellations Eka Rahmawati; Galih Setiawan Nurohim; Candra Agustina; Denny Irawan; Zainal Muttaqin
Jurnal Teknologi Informasi dan Terapan Vol 11 No 2 (2024): December
Publisher : Jurusan Teknologi Informasi Politeknik Negeri Jember

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25047/jtit.v11i2.431

The frequent cancellations of hotel room reservations have become a pressing issue for the hospitality industry, especially in high-tourism areas such as Borobudur, Indonesia. This research develops a predictive machine learning (ML) model to identify cancellation probabilities to support proactive decision-making for hotel management. Using datasets from Borobudur-based hotels, key variables such as booking lead time, arrival month, and reservation outcomes were analyzed. Random Forest demonstrated the best performance, achieving an accuracy of 86.36% with a precision of 88.06%, recall of 93.65%, and F1-score of 90.77%. Logistic Regression demonstrated moderate effectiveness, while Bayesian Networks underperformed, highlighting the importance of robust algorithms for such tasks. The findings underscore the potential of ML models, particularly Random Forest, to reduce financial losses and enhance operational efficiency in the hospitality sector by anticipating cancellations and facilitating better resource allocation

Scratch Sebagai Media Stimulasi Kognitif: Penguatan Berpikir Komputasional Berbasis Service Learning pada Pendidikan Dasar Heribertus Ary Setyadi; Wawan Nugroho; Supriyanta Supriyanta; Candra Agustina
WASANA NYATA Vol 10, No 1 (2026)
Publisher : STIE AUB Surakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36587/wasananyata.v10i1.2199

Wacana integrasi kelas pemrograman bagi siswa dasar dan menengah yang diusulkan oleh Wakil Presiden Gibran Rakabuming Raka memicu restrukturisasi kurikulum nasional oleh Kementerian Pendidikan Dasar dan Menengah melalui penyusunan kerangka strategis berbasis coding dan Kecerdasan Buatan (AI). Edukasi pemrograman pada usia dini diproyeksikan mampu menstimulasi penalaran kreatif serta mengonstruksi soft skills abad ke-21 termasuk problem solving, kolaborasi, dan critical thinking, sehingga orientasi siswa bergeser dari konsumen instruksi menjadi arsitek solusi digital. Selaras dengan arah kebijakan tersebut, artikel/kegiatan ini mengkaji program kemitraan bersama Pondok Pesantren dan Panti Asuhan Al Ikhsan Surakarta dalam memitigasi urgensi kesenjangan digital (digital divide) dan keterbatasan logika sistematis siswa. Melalui intervensi teknologis yang terarah, program ini mengombinasikan instruksi teknis dan penguatan psikologis guna memperluas domain kognitif serta membangun efikasi diri siswa. Hasil implementasi menegaskan bahwa sintesis antara metode Service Learning dan platform Scratch efektif mengakselerasi literasi digital serta pertumbuhan kognitif. Transformasi peserta dari pengguna pasif menjadi kreator aktif diindikasikan oleh penguasaan empat pilar Berpikir Komputasional (Computational Thinking): dekomposisi, pengenalan pola, abstraksi, dan perancangan algoritma, yang secara simultan meningkatkan kapabilitas pemecahan masalah secara signifikan.

Title

Found 40 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 40 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 40 Documents
Search