Claim Missing Document
Check
Articles

Peringkasan Teks Berita Online Bahasa Indonesia Menggunakan Algoritma Textrank Berbasis IndoBERT Clay Justin Wowor; Gladly Caren Rorimpandey
Edutik : Jurnal Pendidikan Teknologi Informasi dan Komunikasi Vol. 6 No. 1 (2026): EduTIK : Februari 2026
Publisher : Jurusan PTIK Universitas Negeri Manado

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

Abstract

Pesatnya pertumbuhan informasi berita digital menuntut efisiensi dalam proses konsumsi informasi melalui ringkasan teks otomatis. Penelitian ini bertujuan untuk mengimplementasikan metode peringkasan teks ekstraktif menggunakan integrasi model bahasa IndoBERT dan algoritma TextRank untuk menghasilkan ringkasan berita berbahasa Indonesia yang akurat. Metodologi yang digunakan meliputi tahapan pra-pemrosesan data yang komprehensif untuk mengeliminasi noise jurnalistik, dilanjutkan dengan representasi semantik kalimat menggunakan embedding dari model praterlatih IndoBERT. Hubungan semantik antar kalimat tersebut kemudian dimodelkan ke dalam struktur graf, di mana tingkat kepentingan setiap kalimat dihitung menggunakan algoritma PageRank. Pengujian dilakukan terhadap 3.000 sampel data dari dataset IndoSum. Hasil evaluasi menggunakan metrik ROUGE menunjukkan performa yang menjanjikan dengan nilai rata-rata ROUGE-1 sebesar 0,412, ROUGE-2 sebesar 0,276, dan ROUGE-L sebesar 0,334. Temuan ini mengindikasikan bahwa penggunaan contextual embedding IndoBERT mampu menangkap esensi informasi dan keterkaitan makna antar kalimat secara lebih mendalam dibandingkan metode konvensional. Simpulan dari penelitian ini menunjukkan bahwa integrasi IndoBERT dengan TextRank efektif dalam menghasilkan ringkasan berita yang koheren dan representatif, sehingga layak diaplikasikan sebagai solusi otomasi pengolahan informasi berita di Indonesia.
Web-Based Attendance and Leave Management System with Sequential Search Implementation at Tondano Religious Court Rorimpandey, Gladly C.; Rombon, Natalia Arsel; Kainde, Quido C
Jurnal Teknik Informatika (Jutif) Vol. 7 No. 1 (2026): JUTIF Volume 7, Number 1, February 2026
Publisher : Informatika, Universitas Jenderal Soedirman

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52436/1.jutif.2026.7.1.4896

Abstract

Based on the problems found in the leave application and attendance recording processes at the Religious Court of Tondano, this research was conducted to address these issues through the implementation of the Sequential Search Algorithm in a web-based application. This application aims to manage leave requests and employee attendance efficiently. The existing manual processes, such as paper-based attendance sheets and leave forms requiring multiple physical signatures, have proven to be inefficient, prone to manipulation, and at risk of data loss. To solve these issues, the application was developed using the Rapid Application Development (RAD) method, which enables a faster process in planning, designing, and deploying the system. The implementation of the Sequential Search Algorithm allows for efficient data retrieval, particularly in searching employee leave data without requiring data sorting, thereby simplifying the search process. In addition, the system includes a location-based attendance feature to prevent fraud, ensuring that employees are present within a defined radius before marking attendance. This online system benefits both permanent and non-permanent employees by providing a more secure, accurate, and accessible record of attendance and leave history. This research contributes to the digital transformation efforts of the Religious Court of Tondano by offering an integrated system that supports internal Administration processes and improves overall service quality through the use of information technology.
Implementation of the Advanced Encryption Standard 128 Algorithm in the Web-Based Management Information System Setia Handayani Sinaga; Quido Conferti Kainde; Gladly Caren Rorimpandey
Journal La Multiapp Vol. 7 No. 1 (2026): Journal La Multiapp
Publisher : Newinera Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37899/journallamultiapp.v7i1.2622

Abstract

The manual management of student dormitory administration at Manado State University presents several challenges, particularly related to record accuracy, service effectiveness, and information protection. This research focuses on the development of a web-based dormitory management information system using the Advanced Encryption Standard (AES) 128-bit algorithm as a data security mechanism, particularly for payment documents. The research method used is a prototype model, which includes communication, rapid planning, modeling, prototype development, and testing. The system is implemented using PHP and MySQL, with the integration of AES-128 encryption in the payment receipt upload feature to ensure data confidentiality. The results of black-box testing show that all system functions run according to user requirements. The implementation of AES-128 has been proven to maintain the security of sensitive data and increase user trust in the system. Key features provided include user registration, room reservations, payments, facility reporting, and notifications, while administrators are given full access rights to manage resident and room data, as well as encrypt and decrypt important information. Overall, this research produces a system that not only improves the efficiency and effectiveness of dormitory management but also strengthens data security aspects. The developed system has the potential for further enhancement through mobile application integration and the implementation of an automated payment system to be more responsive to user needs. Cryptography is a field of science that utilizes mathematical techniques to ensure data and information security, including authentication, integrity, and validity
Sistem Informasi Buku Tamu Di Sekretariat DPRD Kabupaten Minahasa Berbasis Web Dengan Metode Prototype Syalomita Cinta; Gladly Caren Rorimpandey
Jurnal Media Computer Science Vol 5 No 1 (2026): Januari
Publisher : LPPJPHKI Universitas Dehasen Bengkulu

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37676/jmcs.v5i1.9068

Abstract

The Secretariat of the Regional House of Representatives (DPRD) of Minahasa Regency currently still uses a traditional method for recording guest book entries, namely manually using paper. This method leads to several issues, such as inefficiency in data retrieval, the risk of information loss, and difficulty in summarizing visit data. To address these issues, a web-based guest book information system was developed using the prototype software development method. This method was chosen because it allows the system to be developed incrementally with active user participation during the design and evaluation stages. The designed system includes key features such as digital guest data entry, the ability to search for data based on specific criteria, and automatic generation of visit reports. Testing results show that this system can simplify the process of recording and managing guest data at the DPRD Secretariat of Minahasa Regency. With the implementation of this system, it is expected that there will be a significant improvement in work efficiency and data accuracy.
Web-Based Incoming And Outgoing Mail Information System As An Effort To Optimize Administration At The Secretariat Of The Regional House Of Representatives (DPRD) Of Minahasa Regency Using The Prototype Method Brandon Natanael Gerungan; Gladly Caren Rorimpandey
Jurnal Media Computer Science Vol 5 No 1 (2026): Januari
Publisher : LPPJPHKI Universitas Dehasen Bengkulu

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37676/jmcs.v5i1.9069

Abstract

Correspondence administration is one of the key aspects in supporting the smooth functioning of bureaucracy in government institutions, including at the Secretariat of the Regional House of Representatives (DPRD) of Minahasa Regency. The current manual management of incoming and outgoing letters often leads to various issues, such as delays in recording, data entry errors, and difficulties in retrieving archived correspondence. Therefore, this study aims to design and develop a web-based information system for managing incoming and outgoing letters to optimize administrative processes within the DPRD Secretariat. The system development follows the prototype method, which allows users to provide direct feedback on the initial system model for iterative improvements. The result of this research is a web-based application that facilitates effective and efficient recording, archiving, searching, and reporting of correspondence. With the implementation of this system, it is expected that the letter administration process at the Secretariat of the DPRD Minahasa Regency will become faster, more accurate, and well-documented.
Penerapan Algoritma Greedy Pada Aplikasi Pelayanan GGP Wilayah Baruppu’ Berbasis Web Jessica Daniel Joni; Quido C. Kainde; Gladly Caren Rorimpandey
IKRA-ITH Informatika : Jurnal Komputer dan Informatika Vol. 10 No. 1 (2026): IKRAITH-INFORMATIKA Vol 10 No 1 Maret 2026
Publisher : Fakultas Teknik Universitas Persada Indonesia YAI

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

Abstract

Pelrkelmbangan telknologi informasi yang selmakin maju tellah melmbelrikan kelmudahan bagi belrbagai bidang, telrmasuk pada selktor kelagamaan. Gelrelja selbagai organisasi kelrohanian melmbutuhkan sistelm informasi yang mampu melndukung manajelmeln pellayanan, pelnyelbaran informasi ibadah, selrta pelndataan jelmaat selcara elfelktif dan elfisieln. Di Gelrelja Gelrakan Pelntakosta (GGP) Wilayah Baruppu’, pelnyampaian informasi jadwal pellayanan masih dilakukan selcara manual mellalui meldia kelrtas, selhingga tidak melrata ditelrima olelh jelmaat dan melnyulitkan pimpinan wilayah dalam melmpelrolelh data jelmaat keltika telrjadi pelrubahan. Untuk itu, pelnellitian ini melrancang aplikasi pellayanan GGP Wilayah Baruppu’ belrbasis welb delngan melnelrapkan algoritma Greleldy dalam prosels pelnjadwalan ibadah. Algoritma Greleldy dipilih karelna mampu melneltapkan kelputusan telrbaik selcara lokal pada seltiap langkah, selhingga melndukung prosels pelnjadwalan ibadah tanpa telrjadinya suatu belntrokan waktu, telmpat dan yang mellayani. Pelnellitian ini belrtujuan melrancang sistelm Pellayanan GGP Wilayah Baruppu’ delngan melnggunakan Algoritma Greleldy, untuk melmbantu melmudahkan pimpinan dan pelngurus dalam melngellola jadwal pellayanan yang ada dalam organisasi GGP Wilayah Baruppu’. Meltodel pelngelmbangan sistelm melnggunakan pelndelkatan prototypel yang melmungkinkan pelngguna mellakukan elvaluasi seljak tahap rancangan awal hingga implelmelntasi. Hasil pelnellitian melnunjukkan bahwa aplikasi yang dikelmbangkan mampu melnyeldiakan pelnjadwalan pellayanan selcara otomatis tanpa telrjadi belntrokan, melnyajikan informasi pellayanan dan ibadah selcara akurat, selrta melmudahkan prosels pelndataan jelmaat olelh pelngurus wilayah. Delngan delmikian, sistelm ini dapat melndukung pelningkatan elfelktivitas manajelmeln pellayanan dan pelngellolaan data jelmaat di GGP Wilayah Baruppu’.
Unemployment Forecasting in North Sulawesi Using a Long Short-term Memory (LSTM) Algorithm Melati Roring; Gladly Caren Rorimpandey; Kristofel Santa
INSERT : Information System and Emerging Technology Journal Vol. 7 No. 1 (2026)
Publisher : Information System Study Program, Faculty of Engineering and Vocational, Undiksha

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23887/insert.v7i1.111436

Abstract

Unemployment remains a key socio-economic indicator that reflects both economic performance and human development conditions at the regional level. In North Sulawesi Province, unemployment levels have shown noticeable fluctuations over the past two decades, driven by changes in labour market structure, workforce characteristics, and development outcomes. This study aims to forecast the number of unemployed people in North Sulawesi by applying a multivariate Long Short-Term Memory model capable of capturing long-term temporal dependencies in time-series data. The analysis uses annual data published by Statistics Indonesia for the period 2000–2025. Several explanatory variables are selected through Pearson correlation analysis, including the Open Unemployment Rate, the number of unemployed women, the population that has never been employed, and the Human Development Index. All variables are normalised and transformed into five-year sliding windows to preserve temporal relationships. The model is constructed using a single hidden layer with 32 units and a dropout rate of 0.2 and is trained using the Adam optimisation algorithm. The evaluation results indicate that the proposed model achieves satisfactory predictive accuracy, with a Mean Absolute Error of 2,960 persons, a Root Mean Square Error of 3,454 persons, and a Mean Absolute Percentage Error of 3.56 percent. Forecasting results for the 2026–2030 period show a gradual decline in unemployment levels. These findings suggest that the model provides reliable unemployment projections and supports data-driven employment policy planning in North Sulawesi.
Aplikasi Augmented Reality untuk Pembelajaran Organ Vital pada Tubuh Manusia Berbasis Android Tesalonika Gracia Palilingan; Gladly C. Rorimpandey; Quido C. Kainde
JOINTER : Journal of Informatics Engineering Vol 7 No 01 (2026): JOINTER : Journal of Informatics Engineering
Publisher : Program Studi Teknik Informatika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.53682/jointer.v7i01.407

Abstract

This research aims to develop an Augmented Reality (AR) application based on Unity and Vuforia as a learning medium for human vital organs at SMP Negeri 1 Lembean Timur. In the context of education, which increasingly requires innovation, this AR application is expected to overcome the limitations of conventional learning methods that rely only on textbooks and 2D images. By utilizing AR technology, students can see three-dimensional (3D) models of vital organs in real-time, offering better details and more engaging interaction. The research results show that the implementation of the AR application has added a new, more interesting variation for students, making it easier for them to understand the shape, position, and function of vital organs. Additionally, this application provides an effective interactive learning alternative in the Natural Sciences (IPA) subject. Thus, the development of this AR application not only enhances students' understanding but also contributes to learning innovation at SMP Negeri 1 Lembean Timur.
The Implementasi Algoritma Kriptografi AES-128 (RIJNDAEL) Untuk Keamanan Informasi Dokumen Rahasia PT. PLN (PERSERO) UP2B Sistem Minahasa Merlin Aprilia Liow; Gladly Caren Rorimpandey; Alfiansyah Hasibuan
Jurnal Sains Informatika Terapan Vol. 5 No. 1 (2026): Jurnal Sains Informatika Terapan (Februari, 2026)
Publisher : Riset Sinergi Indonesia (RISINDO)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62357/jsit.v5i1.922

Abstract

The rapid advancement of digital technologies in the electricity sector has increased the demand for stronger information security systems, particularly in managing confidential documents that support operational decision-making. PT PLN (Persero) UP2B Sistem Minahasa serves as a critical unit responsible for regulating and monitoring electrical load distribution in North Sulawesi, making the protection of internal documents essential to maintaining operational integrity and confidentiality. However, the current document management process still relies on conventional methods and lacks the support of modern encryption technologies, leaving sensitive data vulnerable to unauthorized access, information leakage, and misuse. These risks became more evident following several data breach incidents reported in 2022 and 2023. This research focuses on developing a digital document security system utilizing the Advanced Encryption Standard (AES-128) algorithm to protect files in PDF, DOCX, XLS, and TXT formats. The research stages include requirement analysis, system design, implementation using PHP, MySQL, and OpenSSL, and performance testing for the encryption and decryption processes. The results indicate that AES-128 efficiently encrypts documents and produces files that cannot be accessed without a valid key, while the decryption process successfully restores the original content with an accuracy level of up to 90%. Overall, the implementation of this system significantly improves document security within UP2B Sistem Minahasa and can serve as a reference for strengthening information security policies across PLN units.
Analisis Dan Prediksi Tren Penyaluran Dana Program Indonesia Pintar Di Sulawesi Utara Menggunakan Algoritma Prophet Friska Regina Maralantang; Gladly Caren Rorimpandey; Efraim R. S. Moningkey
IKRA-ITH Informatika : Jurnal Komputer dan Informatika Vol. 10 No. 2 (2026): IKRAITH-INFORMATIKA Vol 10 No 2 Juli 2026
Publisher : Fakultas Teknik Universitas Persada Indonesia YAI

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

Abstract

Program Indonesia Pintar (PIP) merupakan program bantuan pendidikan yang ditujukan untuk mendukung akses pendidikan bagi peserta didik dari keluarga kurang mampu. Dalam pelaksanaannya, pemantauan penyaluran dana PIP di Provinsi Sulawesi Utara masih dilakukan melalui laporan administratif sehingga belum didukung analisis prediktif yang terstruktur untuk mengidentifikasi pola dan kecenderungan penyaluran dana. Penelitian ini bertujuan menganalisis pola historis penyaluran dana PIP dan mengembangkan model prediksi menggunakan algoritma Prophet. Data yang digunakan berupa laporan penyaluran dana PIP di Provinsi Sulawesi Utara periode 2018-2024 yang mencakup jumlah siswa penerima dan dana yang disalurkan pada jenjang SD, SMP, SMA, dan SMK. Tahapan penelitian meliputi pengumpulan data, preprocessing, analisis dan visualisasi, pengembangan model Prophet, evaluasi, serta implementasi hasil dalam dashboard. Model Prophet menggunakan komponen tren, musiman, dan hari khusus dengan prediksi untuk periode 2025-2029. Evaluasi model menggunakan Root Mean Square Error (RMSE) dan Mean Absolute Error (MAE). Hasil penelitian menunjukkan RMSE sebesar Rp28.198.053.446,10 dan MAE sebesar Rp19.541.719.039,70. Model menghasilkan proyeksi penyaluran dana yang relatif stabil dengan kecenderungan meningkat secara bertahap, sedangkan interval prediksi semakin melebar pada 2028-2029. Hasil penelitian menunjukkan bahwa algoritma Prophet dapat digunakan untuk membantu analisis tren dan penyusunan proyeksi penyaluran dana PIP sebagai informasi pendukung perencanaan anggaran pendidikan.
Co-Authors Alfiansyah Hasibuan Alfrina Mewengkang Archangela G. Repi Audy Aldrin Kenap Ayu Triana Situmorang Batmetan, Johan R Bonenehu, Kurniawan Brandon Natanael Gerungan Chrysilia Rimbing Cindy Pamela C Munaiseche Civita Loho Clay Justin Wowor Efraim R. S. Moningkey Febiola Emilliany Christiani Makarawung Friliandra Valentcia Sumendap Friska Regina Maralantang Gitarosalina Sibarani Glenn D. P. Maramis Grasella Pandey Gupuh, Andi Hamsah Hamsah Hasibuan, Alfiansyah Hendro Maxwell Sumual Henri Rompas HS, Fatimah Hulu, Lena Enjelin Imanuel Wowor Intan, Sondakh Agnes Irene Realyta Halldy Trosi Tangkawarow Jessica Daniel Joni Juliawati Haribae Krina Crisila T. Mawuntu Kristofel Santa Lipan, Kezia Lumataw, Alfred Tenda Lumenta, Harfey Mamonto, Nurmila Mantik, Felitia Theona Geofani Marcelliano Riccardy Anantho Omega Kalitouw Mario Trinto Risky Rettob Martina Lorensa Maswonggo, Vandi Vanda Medi Hermanto Tinambunan Melati Roring Merlin Aprilia Liow Meyn Choudy Riovan Kaotel Moh Ramdhan Arif Kaluku Muhammad Zulkifli Mumpel, Stevyoman Oktavianus Ngovangari, Rivchi Hanni Oliver Simon Hardianto Raharusun Olivia Kembuan parabelem tinno dolf rompas Ponggohong, Alfa Riegel Imanuel Quido Conferti Kainde Ramdan Adjis Rapar, Pedro Vincensius Rawung, Lanamey Praisy Indiana Readel Lantang Beryl Mangkey Refandi Andika Runtu Rombon, Natalia Arsel Rompas, Billy Setia Handayani Sinaga Silalahi, Rike Sondy C. Kumajas Sondy Campvid Kumajas Sondy Campvid Kumajas Stevyoman Oktavianus Mumpel Sulaeman, Raffy Avian Supit, Charenia Syalomita Cinta Tameo, Vito Ernesto Tandiapa, Saron Tandiapa, Solagratia Saron Tesalonika Gracia Palilingan Tiwi, Heri Susan Turnip, Maydupi Astri Vandi V.Maswonggo Vincensius Rapar, Pedro Vira Chlaudia Makahinda Vivi Peggie Rantung