cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Mesran
Contact Email
jurnal.josh@gmail.com
Phone
+6282161108110
Journal Mail Official
jurnal.josh@gmail.com
Editorial Address
Sekretariat Forum Kerjasama Pendidikan Tinggi (FKPT) Jalan Sisingamangaraja No. 338, Medan, Sumatera Utara
Location
Kota medan,
Sumatera utara
INDONESIA
JOURNAL OF INFORMATION SYSTEM RESEARCH (JOSH)
Published by Forum Kerjasama Pendidikan TInggi
ISSN : -     EISSN : 2686228X     DOI : -
Core Subject : Science,
Computer Science & IT Decision Sciences, Operations Research & Management
Artikel yang dimuat melalui proses Blind Review oleh Jurnal JOSH, dengan mempertimbangkan antara lain: terpenuhinya persyaratan baku publikasi jurnal, metodologi riset yang digunakan, dan signifikansi kontribusi hasil riset terhadap pengembangan keilmuan bidang teknologi dan informasi. Fokus Journal of Information System Research (JOSH)
Arjuna Subject : Ilmu Komputer (semua kategori) - Ilmu Komputer (Lain-Lain)
Articles 754 Documents
 70   71   72   73   74 
Klasifikasi Tingkat Keparahan Penyakit Diabetic Retinopathy menggunakan Convolutional Neural Network Ginantra, Ni Luh Wiwik Sri Rahayu; Hendrawati, Theresia; Prasetya, I Kadek Diksa Bayu
Journal of Information System Research (JOSH) Vol 6 No 4 (2025): Juli 2025
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josh.v6i4.7432

Abstract

Diabetic Retinopathy is an eye condition in Diabetes sufferers that causes damage to the retina, which can result in permanent blindness if not treated properly. The initial stage of this disease is the widening of the blood vessels in the eye which, if left untreated, can cause the formation of new blood vessels which can cover the retina of the eye, thereby increasing the risk of vision loss. There are several classes of Diabetic Retinopathy disease; to determine the class you can use the Deep Learning method which can model various data such as images. The classification process is carried out by training a Convolutional Neural Network model on a disease image dataset taken from the Kaggel repository with a total of 5 classes. This research uses a Fine Tuning strategy and the EfficientNetB1 model to determine the performance of the CNN model in the Diabetic Retinopathy Classification process. Based on training results, the EfficientNetB1 model produces 92.51% accuracy in detecting Diabetic Retinopathy. These results show that the model can provide optimal results in the dataset training process.
Analisis Sentimen Aplikasi Gojek Pada Ulasan Pengguna di Google Play Store Menggunakan Metode Support Vector Machine Nugroho, Yoga Adi; Sudarno, Sudarno
Journal of Information System Research (JOSH) Vol 6 No 4 (2025): Juli 2025
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josh.v6i4.7891

Abstract

Gojek is an application that has garnered significant attention in Indonesia, offering a variety of services, including transportation, food delivery, and other on-demand services. This study aims to analyze user sentiment towards the Gojek app downloaded from the Play Store in 2024 using the Support Vector Machine (SVM) method. Data was collected through web scraping, comprising 8,000 reviews. The preprocessing steps included cleaning, case folding, tokenizing, stopword removal, stemming, and lexicon-based labeling, followed by TF-IDF and testing using a confusion matrix with Python. The sentiment labeling results revealed that the majority of reviews were negative at 44.25%, followed by positive sentiment at 36.62%, and neutral sentiment at 19.12%. The testing scheme applied 80% for training and 20% for testing. The analysis results showed an accuracy of 93.69%, recall of 93.66%, precision of 93.65%, and F1-Score of 93.67%. These results indicate that the SVM model is capable of classifying sentiment with a high level of accuracy. These findings can provide valuable insights for Gojek developers to enhance the app's service quality.
Sistem Pendeteksi Kebakaran Berbasis Internet of Things Menggunakan Webhook Discord dengan Alarm Hermanto, Hermanto; Kamdan, Kamdan; Maulana, Afrizal
Journal of Information System Research (JOSH) Vol 6 No 4 (2025): Juli 2025
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josh.v6i4.7909

Abstract

Fires are one of the most devastating disasters, often resulting in major losses—both materially and in terms of human lives. To help reduce these risks, a fast and accurate fire detection system is essential. This study presents the development of a fire detection system based on the Internet of Things (IoT), which integrates Discord Webhook notifications and an alarm system, powered by Fuzzy Logic. The system uses flame, smoke, and gas sensors to detect potential fire hazards in an area. Sensor data is processed using Fuzzy Logic to assess the level of fire risk more accurately, and the Center of Gravity (COG) method is used for defuzzification. When a dangerous condition is detected, the system automatically triggers an alarm, a flashing light, and a blower as preventive actions. Thanks to the IoT integration, real-time alerts can be sent via Discord Webhook, keeping users informed instantly. This approach addresses the lack of systems capable of delivering immediate fire warnings. The results of this research show that the system can effectively provide early fire detection with high accuracy and rapid notifications. When both the flame and gas sensors detect danger, a warning is sent to the user through Discord, and users can also review past events through the system’s web server history. Overall, this system offers a practical and innovative solution to improving safety and disaster response.
Penerapan BERTopic dan Analisis Sentimen Leksikal Pada Ulasan Relevan di Google Maps Mengenai Universitas Pamulang Asyiah, Nilovar; Aktavia, Widodo
Journal of Information System Research (JOSH) Vol 6 No 4 (2025): Juli 2025
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josh.v6i4.8007

Abstract

The rapid advancement of information technology has encouraged the public to actively share reviews through digital platforms such as Google Maps. These reviews are not only informative but also reflect real user opinions and experiences regarding places or institutions, including higher education institutions. This study aims to analyze the main topics and sentiment classification contained in Google Maps reviews related to Universitas Pamulang. The approach used in this research combines two main methods. First, topic modeling is conducted using BERTopic, a modern technique based on transformer embeddings and HDBSCAN clustering algorithms, which can capture the semantic context of text more deeply. Second, sentiment analysis is performed using a lexicon-based approach, applying an Indonesian sentiment lexicon to efficiently identify the polarity of opinions without requiring model training.The data analyzed were collected through web scraping of relevant public reviews on Google Maps across four Universitas Pamulang locations: Central Campus, Viktor Campus, Witanaharja Campus, and Unpam Serang. The analysis revealed several dominant topics such as academic services, campus facilities, and bureaucracy. The majority of sentiments identified were neutral to positive, although negative opinions were also found in certain aspects. These findings are expected to serve as strategic input for the university to enhance service quality and strengthen its institutional image in the digital landscape.
Penerapan Metode Analytical Hierarchy Process Dan Tehnique for Order Preference by Similarity to Ideal Solution Dalam Sistem Pendukung Keputusan Penilaian Kinerja Guru Adrian, Leni Junika; Bagye, Wire; Mardi, Mardi
Journal of Information System Research (JOSH) Vol 6 No 4 (2025): Juli 2025
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josh.v6i4.8017

Abstract

The evaluation of honorary teachers’ performance plays a crucial role in efforts to enhance the quality of education. This study aims to assess the performance of honorary teachers at SMK Negeri 1 Praya Tengah by applying the Analytical Hierarchy Process (AHP) and the Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) methods. The assessment is based on four main criteria—pedagogical, personal, social, and professional competencies—which are further broken down into several sub-criteria. AHP is utilized to determine the weight of each criterion according to its level of importance, while TOPSIS is employed to rank the teachers based on their proximity to the ideal solution. The results show that the teacher labeled A3, Susilawati, S.Pd, achieved the highest preference score of 0,831, making her the top-performing honorary teacher. The combination of these methods provides an objective and measurable evaluation that can serve as a valuable reference for decision-making by the school administration.
Implementasi Internet of Things pada Smart Homestay sebagai Solusi Otomatisasi dan Keamanan Akomodasi di Sektor Pariwisata Hermanto, Hermanto; Kamdan, Kamdan; Sanulqi, Ihsan
Journal of Information System Research (JOSH) Vol 6 No 4 (2025): Juli 2025
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josh.v6i4.8033

Abstract

The advancement of Internet of Things (IoT) technology has driven the development of automation systems that enhance comfort and efficiency across various sectors, including hospitality management. This study aims to design and implement a smart homestay system capable of automatically and manually controlling electrical devices using ESP32 and Arduino Uno microcontrollers. The system is equipped with several sensors, such as BH1750 for light intensity detection, MQ2 for smoke and alcohol detection, as well as physical buttons and smart switches for room services including laundry, cleaning, and Do Not Disturb (DND). An Android application, developed using MIT App Inventor, serves as the user interface and communicates with the ESP32 via a local Wi-Fi network using a Web Server method. Experimental results show that the system effectively responds to both sensor input and user commands, displaying real-time data in the app. The automatic light control feature based on lighting levels, gas detection notifications, and room service buttons functioned as designed. The system also supports two-way control between physical buttons and the mobile application. Quantitatively, response times for LED control averaged less than 1 second, sensor readings were updated every 3 seconds, and service command success rates reached 100% in all test scenarios. Therefore, the smart homestay system offers a simple yet effective solution to improve service and comfort in small-scale accommodations.
EduMood: Sistem Deteksi Sentimen Berbasis Web Menggunakan Metode Machine Learning untuk Identifikasi Awal Gejala Stres Mahasiswa Prasetya, Riko Anshori; Rahman, Subhannur; Priyatno, Arif Mudi; Mera, Mera; Wahyuni, Ulfia
Journal of Information System Research (JOSH) Vol 6 No 4 (2025): Juli 2025
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josh.v6i4.8042

Abstract

Students' mental health is an important issue that needs serious attention, especially in the era of social media which is full of psychological pressure. This research aims to develop EduMood, a web-based sentiment analysis system to monitor college students' mental health issues by analyzing tweets on Twitter. The tweet data is collected using relevant keywords and goes through preprocessing stages such as text cleaning, bilingual lexicon-based initial labeling, and balancing the amount of data between sentiment classes. The system uses two machine learning algorithms, Support Vector Machine (SVM) and Naive Bayes with Term Frequency-Inverse Document Frequency (TF-IDF) feature representation. The evaluation results show that SVM has a higher accuracy of 99.3% compared to Naive Bayes which reaches 96.5% with f1 scores for all classes above 0.99 for SVM. EduMood is implemented as a web-based application using Flask and Bootstrap 5, which presents the analysis results through an interactive dashboard. The dashboard displays the aggregate sentiment distribution in the form of diagrams, wordclouds, monitoring tables, and text manual predictions. The results of this study show that EduMood not only provides excellent model performance, but also offers a practical solution for the campus to monitor the psychological condition of students in a fast, real data-based, and easily accessible manner. This system is expected to support efforts to improve student mental health in a sustainable manner.
Optimasi Akurasi Jawaban Aplikasi Chatbot Layanan Pelanggan dengan Metode RAGRetrieval-Augmented Generation Dhaman, Dhaman; Anggai, Sajarwo; Waskita, Arya Adhyaksa
Journal of Information System Research (JOSH) Vol 6 No 4 (2025): Juli 2025
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josh.v6i4.8048

Abstract

This research addresses the issue of low answer accuracy in chatbot systems based on Large Language Models (LLMs) when responding to questions derived from customer service documents. To overcome this problem, the Retrieval-Augmented Generation (RAG) method is applied to improve the quality of responses by adding relevant context from external documents. Three LLM models used in this study are LLaMA3.1 8B, LLaMA3.2 1B, and LLaMA3.2 3B from Meta AI. Evaluation is conducted using automatic ROUGE metrics (ROUGE-1, ROUGE-2, and ROUGE-L) and manual human evaluation assessing accuracy, relevance, and hallucination. This research contributes to the development of more reliable question-answering systems based on LLMs enhanced with external contextual documents related to customer service information. The results show a significant improvement across all models after applying the RAG method. ROUGE F1-scores increased consistently, with Llama3.1:8b showing the highest gain (from 0.12 to 0.58 on ROUGE-1). Human evaluation also confirmed improvements in accuracy (up to +2.73 points) and reductions in hallucination (up to −2.63 points). These improvements were evident not only in larger models but also in smaller ones, indicating that the benefits of RAG are not dependent on model size. In conclusion, RAG is highly effective in enhancing the accuracy and reliability of chatbot responses, especially in document-based question-answering scenarios. By leveraging contextual information from external documents, the system produces more factual, relevant, and hallucination-free responses. RAG has proven to be an effective approach for enhancing the response quality of LLM, including those with smaller parameter sizes.
Klasifikasi Risiko Diabetes Mellitus Menggunakan K-Nearest Neighbors dengan Peningkatan Performa Melalui Teknik Oversampling ADASYN Bagir, Muhammad; Mayatopani, Hendra; Riyanto, Umbar; Alamsyah, Dedy
Journal of Information System Research (JOSH) Vol 6 No 4 (2025): Juli 2025
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josh.v6i4.7237

Abstract

Diabetes mellitus is a chronic metabolic disease with a continuously increasing global prevalence. Early detection of diabetes risk is crucial to reduce long-term health complications and the associated healthcare costs. However, a major challenge in applying machine learning models to medical data is the issue of class imbalance, which can lead to model bias toward the majority class. This study aims to develop a diabetes risk classification model by integrating the K-Nearest Neighbors (KNN) algorithm with the Adaptive Synthetic Sampling (ADASYN) technique to address the class imbalance problem. The dataset used was obtained from the Kaggle platform, containing 2,000 patient samples with nine predictive features. Data preprocessing was performed through missing value imputation, outlier handling using winsorizing, and feature normalization using StandardScaler. ADASYN was applied to generate adaptive synthetic samples for the minority class, and the KNN model was trained and evaluated using confusion matrix, precision, recall, F1-Score, accuracy, and ROC-AUC metrics. The results indicate that the implementation of ADASYN improved the ROC-AUC Score by 5.48% (from 91.34% to 96.82%) and the overall accuracy by 2.50% (from 81.50% to 84.00%). The F1-Score for the Diabetes class also increased by 0.40%. The integration of KNN and ADASYN has proven effective in enhancing model performance for detecting high-risk diabetes patients and improving sensitivity toward the minority class.
Implementasi Metode Webuse Dalam Analisis Usability Pada Website Sistem Informasi Permohonan Online Dukcapil (SEMAIK) Sari, Kadek Dwijayanti Komala; Saikin, Saikin; Zaen, Mohammad Taufan Asri
Journal of Information System Research (JOSH) Vol 6 No 4 (2025): Juli 2025
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josh.v6i4.7442

Abstract

The Department of Population and Civil Registration (Dukcapil) of Central Lombok Regency developed the SEMAIK website to enhance the quality of public services through digital platforms. This website provides official information such as local regulations, announcements, and government programs, while also facilitating communication between the government and the public. This study aims to evaluate the feasibility of the SEMAIK website using the WEBUSE method through an online questionnaire assessing usability aspects. The study involved 120 respondents, and the results showed that three out of four usability dimensions were rated as “Excellent”, with an overall average score of 87%, indicating a very high level of usability. However, the service aspect still needs improvement to achieve optimal user satisfaction. The contribution of this study is to provide a quantitative evaluation of the effectiveness of web-based public services and offer practical references for government institutions in enhancing the quality of digital services.

Page 72 of 76 | Total Record : 754

 70   71   72   73   74 

Filter by Year

2019 2025


Reset
Filter By Issues
All Issue Vol 7 No 1 (2025): Oktober 2025 Vol 6 No 4 (2025): Juli 2025 Vol 6 No 3 (2025): April 2025 Vol 6 No 2 (2025): Januari 2025 Vol 6 No 1 (2024): Oktober 2024 Vol 5 No 4 (2024): Juli 2024 Vol 5 No 3 (2024): April 2024 Vol 5 No 2 (2024): Januari 2024 Vol 5 No 1 (2023): Oktober 2023 Vol 4 No 4 (2023): Juli 2023 Vol 4 No 3 (2023): April 2023 Vol 4 No 2 (2023): January 2023 Vol 4 No 1 (2022): October 2022 Vol 3 No 4 (2022): Juli 2022 Vol 3 No 3 (2022): April 2022 Vol 3 No 2 (2022): Januari 2022 Vol 3 No 1 (2021): Oktober 2021 Vol 2 No 4 (2021): Juli 2021 Vol 2 No 3 (2021): April 2021 Vol 2 No 2 (2021): Januari 2021 Vol 2 No 1 (2020): Oktober 2020 Vol 1 No 4 (2020): JULI 2020 Vol 1 No 3 (2020): April 2020 Vol 1 No 2 (2020): Januari 2020 Vol 1 No 1 (2019): Oktober 2019 More Issue