Article Per Year (5 Year)
p-Index From 2021 - 2026
0.61
P-Index
This Author published in this journals
All Journal Jatilima : Jurnal Multimedia Dan Teknologi Informasi Jurnal Masyarakat Indonesia
Matias Julyus Fika Sirait
Universitas Budi Darma
Chemical Engineering, Chemistry & Bioengineering Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering Education

Published : 3 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 3 Documents
Search

 1 
Implementasi Penulisan Buku Referensi pada Mahasiswa/i Universitas Budi Darma Medan Matias Julyus Fika Sirait; Denni M Rajagukguk
Jurnal Masyarakat Indonesia (Jumas) Vol. 3 No. 02 (2024): Jurnal Masyarakat Indonesia (Jumas)
Publisher : Cattleya Darmaya Fortuna

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

Abstract

This study aims to evaluate the implementation of reference book writing for students of Budi Darma University Medan as an active learning method. Reference book writing is considered as a form of active learning that can improve students' material understanding, research skills, and academic writing. The research method used was a mixed approach, involving surveys, interviews, observations, and document analysis to collect data from students and lecturers involved. The results showed that reference book writing had a significant positive impact on students' material understanding, research skills, and academic writing ability. Most students reported improved understanding and skills after engaging in the project. However, there were some challenges, including difficulties in team coordination, high workload, and problems in editing the material. The discussion revealed that the reference book writing method was effective in deepening students' understanding of the material and improving their academic skills. Nonetheless, the challenges encountered point to the need for better project management strategies and consistent mentorship support. In conclusion, reference book writing as an active learning method proved effective in improving students' academic skills at Universitas Budi Darma Medan. To maximize the results, it is recommended that the university provide additional training, more intensive guidance, and effective project management guidelines. This research provides valuable insights into the implementation of active learning methods and provides recommendations for improvement in its application in higher education.
Workshop Pembuatan Layanan Chatbot Telegram Kampus Berbasis Kecerdasan Buatan Pada Siswa Prakerin SMK Saidi Ramadan Siregar; Matias Julyus Fika Sirait; Hery Sunandar
Jurnal Masyarakat Indonesia (Jumas) Vol. 5 No. 01 (2026): Jurnal Masyarakat Indonesia (Jumas)
Publisher : Cattleya Darmaya Fortuna

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54209/jumas.v5i01.414

Abstract

Perkembangan teknologi informasi menuntut institusi pendidikan untuk menyediakan layanan informasi yang cepat, interaktif, dan dapat diakses kapan saja. Salah satu solusi inovatif untuk memenuhi kebutuhan tersebut adalah pemanfaatan chatbot cerdas. Kegiatan pengabdian masyarakat/workshop ini bertujuan untuk membekali siswa Praktik Kerja Industri (Prakerin) Sekolah Menengah Kejuruan (SMK) dengan keterampilan praktis dalam merancang dan membangun layanan Chatbot Telegram berbasis Artificial Intelligence (AI) untuk pusat informasi kampus. Metode pelaksanaan dibagi menjadi tiga tahapan utama: pemaparan teori, sesi praktik langsung (hands-on), dan evaluasi fungsionalitas. Pendekatan Low-Code/No-Code (LCNC) menggunakan platform n8n yang dijalankan di atas ekosistem Docker diterapkan agar siswa dapat fokus pada algoritma logika tanpa terkendala sintaks pemrograman. Hasil kegiatan menunjukkan peningkatan keterampilan teknis yang signifikan; siswa berhasil mengonfigurasi terowongan jaringan (tunneling) via Ngrok, meregistrasi webhook via BotFather, dan mengintegrasikan agen Kecerdasan Buatan (OpenRouter API) ke dalam alur kerja sistem. Uji coba menunjukkan chatbot mampu melakukan Pemrosesan Bahasa Alami (Natural Language Processing) untuk menjawab kueri informasi secara dinamis dan akurat. Kegiatan ini tidak hanya menghasilkan prototipe layanan digital kampus, tetapi juga secara efektif meningkatkan daya saing siswa SMK dalam menghadapi era industri 4.0.
Classification of Product Review Sentiment Using Naive Bayes and Support Vector Machine Algorithms Pandi Barita Nauli Simangunsong; Matias Julyus Fika Sirait; Tuti Andriani
Jurnal Multimedia dan Teknologi Informasi (Jatilima) Vol. 7 No. 5 (2026): Jatilima : Jurnal Multimedia Dan Teknologi Informasi
Publisher : Cattleya Darmaya Fortuna

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54209/jatilima.v7i5.2166

Abstract

This review synthesizes research on "Theoretical comparison of Naïve Bayes and Support Vector Machine for sentiment classification of product reviews" to address inconsistencies in algorithm performance and applicability across diverse datasets. The review aimed to evaluate theoretical foundations and practical implementations of both algorithms, benchmark classification metrics, analyze factors influencing performance, assess handling of neutral sentiments, and examine ensemble model efficacy. A systematic analysis of studies from Southeast Asia and related regions was conducted, focusing on supervised learning approaches with varied preprocessing and evaluation metrics. Findings indicate that Support Vector Machine generally achieves higher accuracy, precision, and recall across balanced and large datasets, while Naïve Bayes offers superior computational efficiency and recall in specific contexts. Preprocessing techniques and dataset characteristics significantly affect both algorithms’ robustness, with Support Vector Machine demonstrating greater adaptability to data variability and neutral sentiment classification. Hybrid and ensemble models combining Naïve Bayes and Support Vector Machine consistently improve classification accuracy and robustness but incur higher computational costs and remain underexplored. These results underscore the necessity of context-specific algorithm selection and optimization in sentiment analysis. The review highlights theoretical and practical implications for deploying machine learning classifiers in product review sentiment tasks, emphasizing the balance between accuracy, efficiency, and scalability within resource and data constraints.
Co-Authors Denni M Rajagukguk Hery Sunandar Pandi Barita Nauli Simangunsong Saidi Ramadan Siregar Tuti Andriani