Claim Missing Document
Check
Articles

Implementasi LexRank dan BERT2GPT dalam Auto Summarization Teks Bahasa Indonesia Tristan Bey Kusuma; I Made Widiartha; I Putu Gede Hendra Suputra
Jurnal Nasional Teknologi Informasi dan Aplikasinya Vol. 4 No. 1 (2025): JNATIA Vol. 4, No. 1, November 2025
Publisher : Informatics Department, Faculty of Mathematics and Natural Sciences, Udayana University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24843/JNATIA.2025.v04.i01.p03

Abstract

In Indonesia, with the rapid growth of internet and social media usage, the amount of information produced in the Indonesian language has reached significant levels. This creates challenges in managing and understanding this information quickly and efficiently. Text summarization has emerged as a potential solution to help users organize and summarize information, enabling easier and more efficient access to relevant content. This study discusses the development of an Indonesian text summarization model using the LexRank algorithm. The results show that this model can produce accurate and concise summaries, with ROUGE-L result of 0.91 and also a ROUGE-1 result of 0.31. Developing an Indonesian text summarization model is important because it can help users manage and understand information quickly and efficiently. This study provides a positive contribution to the development of Indonesian text summarization models, by providing evidence that the LexRank model can produce accurate and concise summaries.
SISTEM ANALISIS SENTIMEN TERHADAP APLIKASI SIGNAL-SAMSAT DIGITAL NASIONAL I Ketut Oning Pusparama; I Putu Gede Hendra Suputra
Jurnal Pengabdian Informatika Vol. 4 No. 2 (2026): JUPITA Volume 4 Nomor 2, Februari 2026
Publisher : Jurusan Informatika, Fakultas Matematika dan Ilmu Pengetahuan Alam, Universitas Udayana

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

Abstract

Perkembangan teknologi informasi telah mendorong hadirnya inovasi layanan publik berbasis digital, salah satunya aplikasi SIGNAL (Samsat Digital Nasional) yang memudahkan masyarakat dalam pembayaran pajak kendaraan bermotor secara online. Seiring meningkatnya jumlah unduhan dan ulasan di Google Play Store, banyak pengguna memberikan tanggapan positif maupun negatif terkait aplikasi ini. Analisis sentimen dilakukan untuk mengetahui kecenderungan opini publik terhadap aplikasi SIGNAL. Dengan dibangunnya sebuah sistem analisis sentimen diharapkan mampu untuk memberi gambaran tentang bagaimana performa dari aplikasi SIGNAL. Dirancangnya sistem analisis sentimen ini juga diharapkan dapat dijadikan acuan untuk perancangan sistem kedepannya yang berguna untuk meningkatkan pelayanan yang diberikan kepada masyarakat.
PEMBANGUNAN FITUR APLIKASI DATA REKONSILIASI PADA BANK A Albert Okario; I Putu Gede Hendra Suputra; Made Agung Raharja
Jurnal Pengabdian Informatika Vol. 4 No. 1 (2025): JUPITA Volume 4 Nomor 1, November 2025
Publisher : Jurusan Informatika, Fakultas Matematika dan Ilmu Pengetahuan Alam, Universitas Udayana

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

Abstract

Rekonsiliasi bank adalah proses krusial dalam manajemen keuangan yang bertujuan untuk memastikan konsistensi antara catatan keuangan internal perusahaan dan catatan yang disediakan oleh bank. Proses ini melibatkan verifikasi dan pencocokan transaksi yang tercatat dalam buku besar perusahaan dengan laporan rekening koran dari bank, serta identifikasi dan penyelesaian ketidaksesuaian. Rekonsiliasi bank membantu mendeteksi kesalahan pencatatan, transaksi yang belum tercatat, cek yang belum dicairkan, dan potensi kecurangan. Dengan melakukan rekonsiliasi secara rutin, perusahaan dapat menjaga keakuratan dan integritas data keuangan, mendukung pengambilan keputusan yang lebih baik, dan memastikan kelancaran operasional keuangan. Selain itu, rekonsiliasi bank memainkan peran penting dalam memenuhi persyaratan audit dan regulasi keuangan. Artikel ini membahas langkah-langkah dalam proses rekonsiliasi bank, termasuk verifikasi saldo awal, pencatatan transaksi, pencocokan transaksi, identifikasi dan penyelesaian perbedaan, serta pencatatan saldo akhir. Kemajuan teknologi dan perangkat lunak akuntansi modern telah meningkatkan efisiensi dan akurasi proses rekonsiliasi bank, sehingga membantu perusahaan dalam menjaga transparansi dan keandalan laporan keuangan mereka.
Extractive Summarization in Low-Resource Languages: A Systematic Review Agustiana, Ni Putu Arisya; Sanjaya ER, Ngurah Agus; Hendra Suputra, I Putu Gede; Widiartha, I Made
Eduvest - Journal of Universal Studies Vol. 6 No. 2 (2026): Eduvest - Journal of Universal Studies
Publisher : Green Publisher Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59188/eduvest.v6i2.52390

Abstract

NLP advancements have accelerated Automatic Text Summarization research, but development remains skewed toward high-resource languages. Low-resource languages are underrepresented due to limited digital corpora, scarce linguistic tools, and a lack of locally suitable pre-trained models. This research aims to map, identify, and analyze research trends related to extractive summarization in low-resource languages and to formulate future research directions. This study employs a systematic literature review following the PRISMA 2020 protocol. Articles were collected from the ScienceDirect, IEEE Xplore, and Google Scholar databases, covering the 2020–2025 period. A total of nine publications meeting the inclusion criteria were thoroughly analyzed based on six research questions (RQ) formulated using the PICOC framework. Most studies rely on unsupervised approaches such as TextRank, LexRank, and LSA, with key features including word frequency, sentence position, and semantic proximity. News corpora dominate the domain, while system performance evaluation remains limited to traditional metrics such as ROUGE and F1-Score. Identified challenges include limited annotated datasets, the absence of local NLP models, and a lack of meaning-based evaluation approaches. This study confirms that linguistic inequality persists in text summarization, with most research relying on unsupervised methods and lexical evaluation. To address this, three strategic directions are recommended: developing open, diverse language corpora; adopting adaptable lightweight NLP models; and advancing semantic evaluation approaches. Cross-community and interdisciplinary collaboration is essential for building more inclusive and sustainable automatic text summarization systems.
Evaluasi UI pada Prototype Aplikasi “WeCare” Menggunakan Metode SUS (System Usability Scale) Hammam Akmal Prathama; I Putu Gede Hendra Suputra
Jurnal Nasional Teknologi Informasi dan Aplikasinya Vol. 2 No. 1 (2023): JNATIA Vol. 2, No. 1, November 2023
Publisher : Informatics Department, Faculty of Mathematics and Natural Sciences, Udayana University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24843/JNATIA.2023.v02.i01.p15

Abstract

The user interface is one of the most important factors in building an application. A good user interface has aspects of clarity, conciseness, easy recognition, responsiveness, consistency and has aesthetic content. Without careful preparation and design, certain applications cannot run optimally, and can even cause users to switch to other applications. To evaluate the user interface of an application, we can use many methods. One of them is SUS (System Usability Scale). This method provides a “quick and dirty”, reliable tool for measuring usability. The purpose of this study is to evaluate the quality of the User Interface design on the WeCare Application. Evaluation of the quality of the User Interface design will be carried out using the SUS or System Usability Scale method. Evaluation of quality on the usability aspect is carried out using the SUS questionnaire as an assessment standard. The results of this assessment will determine whether the UI design of the WeCare Application is appropriate or not. Based on the survey conducted, the calculation of the usability value of the WeCare application UI design that was tested using the SUS (System Usability Scale) method obtained an average SUS score of 78,33. By obtaining acceptability ranges in the acceptable category, the grade scale is in class B, and adjective rating is in the good category. 
Analisa Rancangan Desain Antarmuka Aplikasi LibrarySense Menggunakan System Usability Scale Gagas Pradipta Jatmiko; I Putu Gede Hendra Suputra
Jurnal Nasional Teknologi Informasi dan Aplikasinya Vol. 3 No. 1 (2024): JNATIA Vol. 3, No. 1, November 2024
Publisher : Informatics Department, Faculty of Mathematics and Natural Sciences, Udayana University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24843/JNATIA.2024.v03.i01.p16

Abstract

The comfort of the library plays a crucial role in supporting learning activities. Temperature that is too hot or too cold, high levels noise, or the presence of smoke can affect the focus and effectiveness of learning for library users. LibrarySense is an application that utilizes wireless sensor network to monitor the environmental conditions of the library in real-time. The application is designed to assist library managers in improving operational efficiency and facility management, as well as enhancing user experience. The System Usability Scale (SUS) method is employed to evaluate the usability of the application. Literature review is conducted to understand the context of implementing SUS, while user interface design is carried out through wireframing and high-fidelity design. Usability testing is conducted using SUS questionnaires distributed to respondents. The research findings indicate that the LibrarySense application achieves an average SUS score of 81.74, indicating a high level of user satisfaction with usability and user experience. This suggests that the LibrarySense application has the potential to enhance the quality of the library environment and support managers in making more informed decisions. 
Analisis Sentimen Ulasan Aplikasi GoTube Menggunakan Naive Bayes Berbasis Particle Swarm Optimization Maedelien Tiffany Kariesta Simatupang; I Putu Gede Hendra Suputra
Jurnal Nasional Teknologi Informasi dan Aplikasinya Vol. 2 No. 4 (2024): JNATIA Vol. 2, No. 4, Agustus 2024
Publisher : Informatics Department, Faculty of Mathematics and Natural Sciences, Udayana University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24843/JNATIA.2024.v02.i04.p14

Abstract

This research employs the sentiment analysis of GoTube application reviews using Naïve Bayes based on Particle Swarm Optimization (PSO). The study focuses on addressing the challenge of efficiently managing and analyzing user comments in the development of the GoTube application. By implementing automated sentiment analysis using text mining techniques, developers can enhance user experience and save resources. The methodology involves data collection, preprocessing, feature extraction using TF-IDF, classification using Naïve Bayes, and evaluation with various parameters. Additionally, Particle Swarm Optimization is utilized for feature selection to enhance the performance of the Naïve Bayes Classifier. The study aims to contribute to the improvement of GoTube's service quality and user satisfaction. 
Perbandingan Neural Network MLP, KNN, dan Decision Tree untuk Klasifikasi Penyakit Diabetes I Made Prenawa Sida Nanda; I Putu Gede Hendra Suputra
Jurnal Nasional Teknologi Informasi dan Aplikasinya Vol. 2 No. 3 (2024): JNATIA Vol. 2, No. 3, Mei 2024
Publisher : Informatics Department, Faculty of Mathematics and Natural Sciences, Udayana University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24843/JNATIA.2024.v02.i03.p18

Abstract

Diabetes is one of the diseases that has received global attention due to its extensive impact on public health. Most people with diabetes are unaware that they are suffering from this condition, this situation emphasizes the need for improved understanding and more effective treatment of this disease. In an effort to address these challenges, this study compares three machine learning algorithms for diabetes classification, the three algorithms are: Multi-Layer Perceptron (MLP), KNearest Neighbor (KNN), and Decision Tree. Data from the Diabetes Dataset used to train and test these models will go through preprocessing first starting from data cleaning, encoding because there is string data, data distribution analysis where in this study using under sampling to equalize data and normalization using min-max normalization, Evaluation results using Confusion Matrix and Classification Report which contains precision, recall, and f1-score the results of this evaluation show that the Neural Network MLP model achieves the highest accuracy of 90.48%, followed by KNN with 88.15% accuracy, and Decision Tree with 87.24% accuracy. These findings provide important insights in selecting the optimal model for diabetes prediction applications. 
Perancangan Model Ontologi untuk Sistem Pencarian Sepeda Motor Bekas I Kadek Dwi Adnyana; I Putu Gede Hendra Suputra
Jurnal Nasional Teknologi Informasi dan Aplikasinya Vol. 2 No. 2 (2024): JNATIA Vol. 2, No. 2, Februari 2024
Publisher : Informatics Department, Faculty of Mathematics and Natural Sciences, Udayana University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24843/JNATIA.2024.v02.i02.p14

Abstract

Motorcycles are a means of transportation that people often use to meet their daily needs. However, not everyone can afford to buy a new motorbike, so many people are switching to used motorbikes. Finding a used motorcycle that suits your needs can be a difficult challenge for some people and of course there are many factors that must be considered. The solution that can be done for this problem is to use the semantic ontology model with the Methodology method. The design of the ontology model of used motorcycle products uses the protégé application, the ontology model is developed into a structure in protégé with a hierarchical structure of classes, slots, properties, etc. Used motorcycle product ontology development model produces 13 classes, 5 object properties, 5 data properties, and 68 individuals or instances in each class. The ontology evaluation process by performing SPARQL queries is used to get the appropriate results. 
Analisis Celah Keamanan Jaringan WPA dan WPA2 dengan Menggunakan Metode Penetration Testing Albert Okario; I Putu Gede Hendra Suputra
Jurnal Nasional Teknologi Informasi dan Aplikasinya Vol. 1 No. 4 (2023): JNATIA Vol. 1, No. 4, Agustus 2023
Publisher : Informatics Department, Faculty of Mathematics and Natural Sciences, Udayana University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24843/JNATIA.2023.v01.i04.p14

Abstract

With the rapid development of communication and information technology, wireless local area network (WLAN) security has become crucial and a major concern, as data traffic is transmitted without the need for cables. Internet-connected network devices are inherently insecure and can be exploited by crackers or hackers. When data communicates or connects in the data traffic, where data is sent and passes through a series of terminals to reach its destination, an irresponsible user has the opportunity to modify or intercept the data. Therefore, designing a WLAN network connected to the internet must be carefully planned to minimize undesirable incidents. The weakness of the IEEE 802.11 network that uses WEP encryption tends to make the encryption code more easily discoverable by hackers. Based on the aforementioned background, we conducted this research to identify vulnerabilities or security flaws in WPA and WPA2-PSK networks using penetration testing methods. 
Co-Authors Adnyana, I Kadek Dwi Agus Muliantara Agus Zainal Arifin Agustiana, Ni Putu Arisya Aji, Desak Ketut Puri Trisnantya Albert Okario Anak Agung Istri Ngurah Eka Karyawati Anak Agung Sinta Trisnajayanti Anak Agung Sinta Trisnajayanti Anny Yuniarti Ari Wilani, Ni Made Desak Ketut Puri Trisnantya Aji Desak Ketut Puri Trisnantya Aji Era Wahyuni Gagas Pradipta Jatmiko Gde Deva Dimastawan Saputra Gede Aditra Pradnyana Gede Gery Sastrawan Gede Lucky Aldi Arsa Gede Sukadarmika Gorianto, Frisca Olivia Hammam Akmal Prathama Hapsari, Ni Made Alisya Putri Hendrawan, Made Chandra I Dewa Made Bayu Atmaja Darmawan I Dewa Made Bayu Atmaja Darmawan, I Dewa Made Bayu I Gede Arisudana Samanjaya I Gede Arta Wibawa I Gede Ngurah Arya Wira Putra I Gede Santi Astawa I Gede Surya Rahayuda I Gusti Agung Gede Arya Kadyanan I Gusti Ngurah Anom Cahyadi Putra I Kadek Agus Andika Putra I Kadek Dwi Adnyana I Kadek Dwika Pradnyana I Ketut Gede Suhartana I Ketut Gede Suhartana I Ketut Kusuma Merdana I Ketut Oning Pusparama I Komang Kumara Saduadnyana I Made Agus Setiawan I Made Prenawa Sida Nanda I Made Widhi Wirawan I Made Widiartha I Made Widiartha I Putu Agus Wahyu Wirakusuma Putra I Putu Dana Putra I Wayan Supriana Ida Ayu Gde Suwiprabayanti Putra Ida Bagus Gede Dwidasmara Ida Bagus Gede Dwidasmara Ida Bagus Gede Sarasvananda Ida Bagus Made Mahendra Ida Bagus Weda Baskara Adi Putra Indra Permana Putra Ketut Agus Cahyadi Nanda Kevin Moses Waleleng Khaerul Anwar Kompiang Gede Sukadharma Lidya Elisabet Theogracia Silitonga Linawati Linawati Linawati Luh Arida Ayu Rahning Putri Luh Gede Astuti Made Widiartha Maedelien Tiffany Kariesta Simatupang Maheswara, Pande Putu Devo Punda Mohammad Rizky Kustiadie Nanda, Ketut Agus Cahyadi Ngurah Agus Sanjaya ER Ni Made Alisya Putri Hapsari Ni Made Wipra Ranum Ratnayu Ni Putu Subhasini Dewi Sukma Ni Wayan Anti Andari Nyoman Putra Sastra Okario, Albert Pitoy, Pingkan Anggriani Prathama, Hammam Akmal Prebiana, Kiki Dwi Putra, I Putu Dana Putri, Audini Nifira Putu Risky Andrean Raharja, Made Agung Sida Nanda, I Made Prenawa Simarmata, Ivan Luis Simatupang, Maedelien Tiffany Kariesta Sukadarmika, I Gede Tirtana Putra, Made Arya Trisnajayanti, Anak Agung Sinta Tristan Bey Kusuma Yuda, Putu Agus Prawira Dharma