Jurnal Sistem Informasi Dan Informatika

Analisis Efektivitas Algoritma Machine Learning dalam Deteksi Hoaks: Pada Berita Digital Berbahasa Indonesia

M Dicky Desriansyah, Intan Utna Sari, Zulfahmi Zulfahmi — Wed, 18 Jun 2025 00:00:00 +0000

The rapid development of information technology has transformed how society accesses and disseminates information. Unfortunately, this phenomenon also creates opportunities for the massive spread of fake news or hoaxes through digital platforms. This research aims to analyze the effectiveness of several machine learning algorithms in detecting text-based hoaxes in Indonesian. The algorithms tested include Multilayer Perceptron (MLP), Naïve Bayes (NB), Support Vector Machine (SVM), and Random Forest (RF). The data used consists of online news articles that have undergone text preprocessing stages such as tokenizing, case folding, filtering, stopword removal, stemming, and weighting using the TF-IDF method with a combination of unigram and bigram features. Performance evaluation was conducted using precision, recall, F1-score, and accuracy metrics. The results show that the SVM and MLP algorithms yielded the highest performance with evaluation values above 99.8%, while RF demonstrated strong and stable performance, and NB showed decent performance with high efficiency. These findings provide insights into the effectiveness of text classification methods in hoax detection and serve as a reference for developing more efficient and accurate fake news detection systems

Analisis Dampak Kecerdasan Buatan terhadap Transformasi Lapangan Kerja: Studi Literatur Sistematis

Rizky Putra, Sularno Sularno, Zulfahmi Zulfahmi — Sun, 13 Jul 2025 00:00:00 +0000

Perkembangan teknologi Kecerdasan Buatan (Artificial Intelligence/AI) yang pesat menimbulkan spekulasi luas tentang kemampuannya menggantikan tenaga kerja manusia di masa depan. Penelitian ini bertujuan untuk menganalisis secara sistematis bagaimana AI memengaruhi pola kerja dan struktur pekerjaan di berbagai sektor. Melalui kajian literatur sistematis terhadap publikasi ilmiah dari tahun 2017 hingga 2024, penelitian ini mengidentifikasi jenis pekerjaan yang paling rentan terhadap otomatisasi, sektor yang berpotensi tumbuh, serta respons strategis yang diperlukan di tingkat kebijakan dan organisasi. Hasil kajian menunjukkan bahwa AI cenderung menggantikan tugas-tugas yang repetitif dan berbasis aturan, namun pada saat yang sama menciptakan peluang baru di bidang kreatif, analitik, dan digital. Studi ini menekankan pentingnya inisiatif peningkatan keterampilan dan strategi adaptif tenaga kerja dalam menghadapi disrupsi akibat AI. Temuan ini memberikan kontribusi terhadap diskursus dampak sosial ekonomi AI dan pengembangan sistem informasi yang berorientasi masa depan

Evolusi Multimodal AI dalam Pendidikan: Inovasi GPT-5, Gemini Ultra, dan Transformasi Pembelajaran Digital

Okki Ramadhan, Intan Utna Sari, Sularno Sularno — Sun, 13 Jul 2025 00:00:00 +0000

The development of artificial intelligence (AI) technology continues to experience significant advancements, particularly with the emergence of multimodal models such as OpenAI’s GPT-5 and Google DeepMind’s Gemini Ultra. These innovations mark the beginning of a new phase in AI utilization, where the technology is not only capable of understanding and generating text, but also processing images, audio, and video simultaneously. This capability opens up numerous opportunities in the field of education, especially in creating more interactive, personalized, and adaptable learning models tailored to students’ needs.

The purpose of this article is to examine how the evolution of multimodal AI impacts digital-based educational practices, with a special focus on the potential and applications of GPT-5 and Gemini Ultra in the teaching process. A literature review method is employed to analyze the latest scientific and technical publications regarding AI implementation in education. The analysis focuses on technological capabilities, types of learning interventions, and potential risks and challenges that may arise.

The findings indicate that multimodal AI can not only enhance the accessibility and effectiveness of learning but also facilitate the creation of more inclusive and contextual learning experiences. However, the implementation of such technologies requires strong regulations and ethical norms to prevent issues such as data privacy violations, unequal access to technology, and reduced human interaction in educational settings.Therefore, this article recommends a balanced use of multimodal AI—one that harmonizes technological innovation with human-centered pedagogical principles—to ensure that the digital transformation in education proceeds sustainably and equitably.

Pengaruh UI/UX terhadap Kepuasan Pengguna Aplikasi Rental Motor

Misari Handayani, Intan Utna Sari, Putri Anggraini — Sun, 13 Jul 2025 00:00:00 +0000

Perkembangan teknologi digital mendorong berbagai layanan beralih ke platform digital, termasuk layanan rental motor. Dalam pengembangan aplikasi, UI (User Interface) dan UX (User Experience) jadi dua komponen penting untuk memastikan kenyamanan pengguna. Studi literatur ini membahas bagaimana pengaruh desain antarmuka (UI) dan pengalaman pengguna (UX) terhadap kepuasan pengguna dalam menggunakan aplikasi rental motor. Hasil kajian dari beberapa penelitian terdahulu menunjukkan bahwa tampilan aplikasi yang menarik, navigasi yang mudah, serta responsivitas aplikasi sangat berpengaruh terhadap persepsi dan kepuasan pengguna.

Analisis Konseptual Desain UI UX pada Aplikasi Dompetku dalam Meningkatkan Pengalaman Pengguna

Septia Wulandari, Putri Anggraini, Faradika Faradika — Sun, 13 Jul 2025 00:00:00 +0000

Dompet digital telah menjadi salah satu inovasi penting dalam perkembangan teknologi keuangan modern, memberikan kemudahan dalam transaksi non-tunai melalui perangkat seluler. Namun, keberhasilan aplikasi tidak hanya bergantung pada fungsionalitas, tetapi juga pada bagaimana pengguna merasakan dan menilai interaksi dengan antarmuka. Penelitian ini bertujuan untuk melakukan analisis konseptual terhadap desain UI (User Interface) dan UX (User Experience) pada aplikasi "Dompetku" guna mengidentifikasi prinsip-prinsip desain yang dapat meningkatkan pengalaman pengguna. Metode yang digunakan adalah studi literatur terhadap berbagai pendekatan evaluasi seperti User Experience Questionnaire (UEQ), Heuristic Evaluation, System Usability Scale (SUS), Design Thinking, dan Human-Centered Design (HCD). Hasil analisis menunjukkan bahwa aspek seperti kejelasan tampilan (perspicuity), efisiensi alur transaksi, dan daya tarik visual sangat memengaruhi kenyamanan pengguna. Selain itu, aspek kebaruan dan personalisasi juga perlu ditingkatkan agar aplikasi lebih kompetitif di pasar. Penelitian ini memberikan usulan desain konseptual yang dapat diterapkan oleh pengembang untuk menciptakan antarmuka yang lebih intuitif, efisien, dan berorientasi pada pengguna. Diharapkan hasil analisis ini dapat menjadi acuan awal dalam pengembangan lebih lanjut aplikasi "Dompetku".

Perancangan Sistem Smart Home Berbasis IoT Menggunakan ESP32 dan Aplikasi Blynk untuk Otomatisasi Perangkat Rumah Tangga

Poppy Rahayu, Sularno Sularno, Intan Utna Sari — Sun, 13 Jul 2025 00:00:00 +0000

This study aims to design and implement an Internet of Things (IoT)-based smart home system capable of controlling household devices using an ESP32 module and the Blynk application. The background of this research is the need for an efficient, practical, and remote-accessible home automation system. The methodology follows the Extreme Programming (XP) model, covering planning, design, coding, and testing stages. The implementation results demonstrate that the system can control devices such as lights, fans, and water pumps via smartphone in real-time. The system also shows high operational efficiency and user-friendliness. This research contributes to the advancement of smart home technology by providing an economical and easy-to-implement solution.

Keywords: Smart Home; Internet of Things; ESP32; Blynk; Automation.

ChatGPT sebagai Tutor Virtual: Dampaknya terhadap Kemampuan Critical Thinking

Westi Bawarta, Faradika Faradika, Intan Utna Sari — Sun, 13 Jul 2025 00:00:00 +0000

This study aims to evaluate the impact of using ChatGPT as a virtual tutor on the critical thinking skills of university students in Indonesia. The research is grounded in the growing integration of artificial intelligence technologies in higher education, particularly in self-directed learning processes. A quantitative research method was employed using an experimental survey approach, in which respondents were divided into two groups: an experimental group using ChatGPT as a tutor and a control group using conventional learning methods. Data collection instruments included a critical thinking skills test and a student perception questionnaire. The results revealed a significant improvement in the critical thinking abilities of the experimental group compared to the control group. Students who used ChatGPT demonstrated stronger skills in analyzing arguments, drawing conclusions, and evaluating information objectively. The study concludes that ChatGPT holds potential as an effective learning tool to enhance critical thinking abilities. The implications suggest the wise integration of ChatGPT into higher education systems, while also considering ethical aspects and supervision in its use.

Deteksi Serangan Siber Menggunakan Machine Learning: Studi Pada Sistem Informasi Akademik

Cantika Chandra, Dio Prima Mulya, Faradika Faradika — Sun, 13 Jul 2025 00:00:00 +0000

Keamanan siber menjadi isu krusial dalam sistem informasi akademik yang menyimpan data sensitif seperti nilai, identitas mahasiswa, dan dokumen administrasi. Serangan seperti SQL injection, brute force login, hingga akses ilegal dapat menyebabkan kerugian besar dan gangguan operasional. Penelitian ini bertujuan mengembangkan sistem deteksi serangan siber menggunakan algoritma machine learning yang mampu mengenali aktivitas tidak normal (anomali) dalam sistem. Algoritma yang digunakan adalah Decision Tree dan Random Forest karena kemampuannya dalam klasifikasi dan interpretasi hasil. Penelitian dilakukan dengan mengumpulkan data log aktivitas pengguna, membersihkannya, melabeli data, kemudian melatih model ML. Hasil evaluasi menunjukkan bahwa Random Forest lebih unggul dengan akurasi 92% dalam mendeteksi serangan dibandingkan Decision Tree yang mencapai 87%. Penerapan sistem ini mampu membantu pihak IT kampus melakukan pencegahan dan respons lebih cepat terhadap ancaman siber.

Perancangan Sistem Informasi Manajemen Aset Pada Fakultas Farmasi Universitas Andalas

Eka Iswandy, Alhamidi Alhamidi, Rini Asmara, Arif Budiman — Mon, 11 Aug 2025 00:00:00 +0000

Designing and developing a web-based asset management information system for the Faculty of Pharmacy at Andalas University. The increase in the number of physical assets and the absence of a centralized management system have caused various problems in the process of recording, tracking, and reporting assets. This study employs the System Development Life Cycle (SDLC) approach, which includes the stages of planning, analysis, design, implementation, testing, and system maintenance. The developed system consists of several main modules, such as asset data entry, room management, asset movement tracking, and asset reporting. The implementation results show that the system can improve data accuracy, facilitate the tracking of asset conditions and locations, and support real-time data-driven decision-making.