Journal Software, Hardware and Information Technology

Penerapan Machine Learning untuk Klasifikasi Teks Depresi pada Kesehatan Mental dengan SVM, TF-IDF, dan Chi-Square

Mon, 30 Jun 2025 00:00:00 +0800

Mental health has become a crucial global issue, with increasing numbers of individuals expressing their psychological conditions openly on social media platforms. This study aims to classify tweets related to mental health, specifically depression, using a combination of Support Vector Machine (SVM), Term Frequency-Inverse Document Frequency (TF-IDF) feature extraction, and Chi-Square feature selection techniques. Although this approach has been widely applied in domains such as product and movie reviews, its application in the mental health context remains limited. The main challenge lies in capturing implicit psychological nuances and indirect expressions frequently present in platforms like Twitter, unlike the explicit text in other domains. Moreover, most prior studies have not integrated comprehensive preprocessing stages including lemmatization, stopword removal, and duplicate elimination for mental health data on social media. This research employs a dataset of 26,448 tweets derived from Kaggle and self-crawled data. The best result was achieved using an SVM with an RBF kernel without Chi-Square feature selection, yielding an accuracy of 74.93%. The study demonstrates that a comprehensive preprocessing pipeline can enhance classification performance. However, the model still struggles with sarcastic or ironic contexts. Future research is recommended to adopt deep learning approaches such as BERT or LSTM to capture more complex textual contexts.

Deteksi Penyakit pada Daun Tomat Menggunakan Kombinasi Ekstraksi Fitur Colors Moments dan Grey Level Co-Occurrence Matrix (GLCM)

Ririn Suharni Syarif, Muhammad Nur Akbar, Darmatasia — Mon, 30 Jun 2025 00:00:00 +0800

Tomato is one of the leading horticultural crops widely cultivated by farmers in Indonesia. In addition to its high economic value, tomatoes are rich in nutrients beneficial to human health, such as vitamin C, lycopene, and other antioxidants. However, tomato productivity is highly vulnerable to decline due to various diseases, particularly those affecting the leaves. These diseases not only reduce the quality of the harvest but also significantly threaten production quantity. Therefore, early detection of leaf diseases in tomato plants is essential to help farmers, especially novice farmers, take timely and appropriate treatment actions. This study aims to develop a digital image-based detection system for tomato leaf diseases using feature extraction methods and classification algorithms. In the image pre-processing and feature extraction stages, the Color Moments algorithm is used to capture color information, while the Gray Level Co-occurrence Matrix (GLCM) represents leaf texture. The classification process is carried out using the Random Forest algorithm. The dataset used in this study was obtained from Kaggle, consisting of 5,451 images of tomato leaves categorized into six classes: Leaf Spot, Leaf Mold, Septoria Leaf Spot, Mosaic Virus, Bacterial Spot, and Healthy Leaf. Test results show that the developed model achieved an accuracy of 90%. These findings indicate that the system can detect tomato leaf diseases with a relatively high level of accuracy. The system is expected to assist farmers, especially beginners, in identifying plant diseases more quickly and accurately, thereby improving treatment efficiency and increasing crop yields.

Pengembangan Landing Page untuk Mendukung Digitalisasi PT Kosa Group Indonesia Menggunakan Platform Low-Code

Arswenda Jameci Irawan, Jefri Marzal, Mutia Fadhila Putri — Mon, 30 Jun 2025 00:00:00 +0800

This study aims to develop a landing page as part of the digitalization strategy of PT Kosa Group Indonesia, a culinary company consisting of three main divisions: Kosarasa, Kosa Team, and Risafood. The development followed the waterfall method through observation, literature review, system design, implementation, and testing. The Framer platform was selected as a low-code solution due to its efficiency in building responsive, maintainable interfaces without the need for complex programming. This initiative was driven by the limitations of previously used platforms such as LinkTree, which lacked the capability for visual customization and did not effectively unify multi-division information. Performance testing using Google PageSpeed Insights showed an increase from 44 to 54 on mobile and from 44 to 55 on desktop after visual and structural optimizations. Usability testing using the System Usability Scale (SUS) yielded an average score of 87.25, which is categorized as excellent. The results indicate that low-code-based landing page development offers an effective solution to support business digitalization in the culinary sector, while maintaining development efficiency, strong visual identity, and user-friendly experience.

Analisa Pola Penyebaran Pengguna Layanan Transjakarta dengan Metode K-Means Clustering

Mon, 30 Jun 2025 00:00:00 +0800

This study analyzes the spatial distribution patterns of Transjakarta service users in Jakarta using the K-Means Clustering algorithm. The dataset, obtained from the Kaggle platform, consists of 189,501 passenger transaction records, including tap-in and tap-out locations, travel times, and user-related information. The research process involves data collection, preprocessing to remove missing values, application of the K-Means Clustering algorithm, and determination of the optimal number of clusters using the elbow method. Based on the analysis, the optimal number of clusters is identified as four (K=4). A scatter plot visualization presents user distribution patterns based on geographic coordinates and service usage times. Each cluster represents a group of users with similar travel characteristics. This analysis results in a segmentation that reflects variations in Transjakarta passenger mobility patterns and illustrates how travel activity is distributed across spatial and temporal dimensions within the urban area of Jakarta.

Perbandingan Kinerja Model Pembelajaran Mesin Random Forest dan K-Nearest Neighbor (KNN) untuk Prediksi Risiko Kredit pada Layanan Pinjaman Online

Santi Prayudani, Yous Sibarani, Azrizal Salam, Arif Ridho Lubis — Mon, 30 Jun 2025 00:00:00 +0800

This study aims to compare the performance of two popular machine learning algorithms, Random Forest and K-Nearest Neighbor (KNN), in predicting creditworthiness in online lending systems. The research uses the publicly available Loan Approval Prediction Dataset from Kaggle, which contains borrower profiles such as employment status, number of dependents, annual income, loan amount, loan term, and credit score. Data preprocessing included cleaning, handling missing values, outlier removal, and transformation through normalization and encoding. The dataset was divided into 80% training data and 20% testing data. Random Forest was configured with 100 decision trees and unlimited depth, while KNN used an optimal k value of 5 determined by grid search. Model performance was evaluated using accuracy, precision, recall, and F1-score. The results showed that Random Forest outperformed KNN with consistently higher values (97%) across all metrics, demonstrating strong stability and superior pattern recognition capabilities. KNN, with an accuracy of 89%, still showed good performance and can be considered a lightweight alternative for simpler applications.

Perancangan Sistem Mobile Reporting Berbasis Android untuk Pelaporan Preventive dan Corrective Maintenance di PT Telkom Indonesia Divisi Regional V

Nova Andre Saputra, Yulius Hari, Darmanto — Mon, 30 Jun 2025 00:00:00 +0800

Preventive, corrective, and maintenance activities are crucial tasks in the NE & OM Division of PT Telkom Indonesia Regional V. Despite the availability of a reporting system through Telegram bot and PACMAN-NEO web, the recording and reporting process is still considered less than optimal and is often complained about at the regional level. The main problems include data inaccuracy, lack of innovation and credibility, and visualization that has not met user expectations. This research aims to overcome the problems of slow, inaccurate, and less real-time reporting, as well as improve the features of navigation, verification, and monitoring of technician activities. The development method used is the System Development Life Cycle (SDLC) Waterfall model. The application was developed using Dart and Flutter as front-end frameworks, PHP and Laravel for API management, and PostgreSQL as the database. The black box test results show that all features function according to user needs. This application has been tested by 3 regional managers, 4 witel managers, 1 regional admin, and 10 technicians. User evaluation showed results of 75% for usability, 63% for ease of use, and 78% for user satisfaction. These results indicate that the developed application is feasible to use as a replacement for the previous Telegram-based PACMAN-NEO system.

Penerapan Natural Language Processing (NLP) dengan Metode Cosine Similarity pada Sistem E-Monev untuk Pencarian Program Pembangunan Daerah

Moch Faizal Ansyori, Ahmad Heru Mujianto — Mon, 30 Jun 2025 00:00:00 +0800

The Evaluation and Monitoring System (E-Monev) is a digital tool utilized for the periodic oversight of performance achievements and budget absorption within Regional Government Organizations (OPD). A primary challenge in its implementation lies in accurately identifying relevant regional development programs based on user text input. Conventional keyword-based search approaches are limited in their ability to comprehensively understand the semantic meaning of text, frequently yielding inaccurate or contextually irrelevant results. This study aims to design and develop a semantic search feature for the E-Monev system. It applies a Natural Language Processing (NLP) approach, employing the Cosine Similarity method and text representation based on BERT (Bidirectional Encoder Representations from Transformers). The data for this research was sourced from the Work Plan (Renja) documents of all OPDs in Bojonegoro Regency. These Renja documents were prepared in accordance with the Decree of the Minister of Home Affairs Number 900.1.15.5-3406 of 2024, which constitutes the Second Amendment to Decree of the Minister of Home Affairs Number 050-5889 of 2021, regulating the verification, validation, and inventory of updates to the classification, codification, and nomenclature of regional development and financial planning. During the analysis, both user input texts and Renja data were converted into embedding vectors, from which their semantic similarity was calculated. Test results demonstrate that the developed system significantly improves search accuracy, achieving a precision value of 0.884.

Pengujian Sistem Identitas Digital Siswa Berbasis Blockchain untuk Keamanan dan Transparansi Menggunakan Black-Box Testing

Berta Erwin Slam, Feri Irawan, Nolan Efranda, Rifaldi Herikson — Mon, 30 Jun 2025 00:00:00 +0800

This study proposes a blockchain-based student identity card system as a secure and transparent solution for managing digital identities at the senior high school level. The system is designed to address various issues found in conventional identification methods, such as data forgery, physical card damage, and limited verification capabilities. Developed using the Laravel framework and integrated with a private blockchain network, student identity data is hashed and stored permanently. The digital identity is represented as a QR code printed on the student ID card. Identity verification can be performed independently through a web-based application without relying on a central authority. System evaluation was conducted through functional testing using the black-box testing method, as well as user testing to assess reliability, efficiency, and usability. Test results showed that the system was able to verify identities with an average QR code response time of less than 3 seconds and a login success rate of 98%. Therefore, the integration of blockchain technology into the web platform proves to be an innovative and feasible approach to modernizing student identity management. This system contributes to strengthening the digital transformation of secondary education in a secure, efficient, and decentralized manner.