Journal of Computer Science and Technology (JCS-TECH)

PENERAPAN LEXICON-BASED LABELING UNTUK ANALISIS SENTIMEN ULASAN UMKM KULINER DENGAN PERBANDINGAN KINERJA ALGORITMA MACHINE LEARNING

2026-04-05T19:36:38+07:00

This study aims to classify consumer sentiment of culinary MSMEs in South Kalimantan using a hybrid approach that combines Lexicon-Based methods and Machine Learning algorithms. The dataset used is a collection of MSME consumer reviews written on social media Instagram and Twitter (X). Lexicon-based is used for automatic labeling based on positive and negative word dictionaries, while Machine Learning algorithms (Naïve Bayes, Random Forest, Logistic Regression, Support Vector Machine (SVM), Decision Tree, and K-Nearest Neighbors (KNN)) as a model to determine the results of pattern-based sentiment classification. The research stages include dataset collection, text preprocessing, automatic labeling using lexicon-based labeling, TF-IDF feature extraction, model implementation with Machine Learning and evaluation of results using classification metrics (accuracy, precision, recall and F1-score), then comparative analysis between models to determine which model has the best performance in classifying MSME consumer review sentiment. The results showed that the Support Vector Machine model produced the best accuracy (79%) and an F1-score of 70%, followed by Logistic Regression with 77% accuracy and 77% precision. Both models performed better in classification than Naive Bayes and Random Forest, while the tree-based model was considered suboptimal. The results of this study are expected to contribute and serve as a reference for culinary MSMEs in East Kalimantan in understanding consumer perceptions to improve product and service quality

IMPLEMENTATION OF DATA MASKING TECHNIQUES FOR CUSTOMER DATA PROTECTION ON E-COMMERCE WEBSITES

2026-04-23T09:43:15+07:00

Customer data security is an important aspect in managing e-commerce websites because such systems store sensitive information such as phone numbers, email addresses, and transaction histories. If not properly protected, this data may lead to breaches and misuse by unauthorized parties. This study aims to implement a data masking technique as a solution for protecting customer data on an e-commerce website. The research method used was Action Research, consisting of planning, action, observation, and evaluation stages. The data masking technique was applied by disguising all sensitive data characters using specific symbols without changing the original data stored in the database. System testing was conducted using Blackbox Testing and User Acceptance Testing (UAT) involving 293 respondents. The results showed that all system features functioned properly, with a UAT score of 85.37%, categorized as very good. This study contributes to the development of information security systems through the application of data masking as a method for protecting customer privacy in website-based digital services. Therefore, the developed system is effective and feasible to be implemented on e-commerce platforms to improve customer data security.

OPTIMIZATION OF WORKFORCE ASSIGNMENT USING THE HUNGARIAN METHOD BASED ON POM-QM IN A BARBERSHOP BUSINESS

2026-04-05T19:37:33+07:00

This study discusses Skill Daeng, a barbershop business established on April 9, 2018, located at Km.9 next to the PLTD, Malaingkedi Village, Malaimsimsa District, Sorong City, Southwest Papua. Skill Daeng offers three main services: barbershop, perming, and smoothing, run by two workers, Nanang and Baim. In one week, the profit from the barbershop service obtained is IDR 2,125,000 for Nanang and IDR 1,370,000 for Baim. In addition, both workers also earn additional income from perming services of IDR 200,000 and smoothing of IDR 140,000. However, the current division of tasks is not optimal, which causes an imbalance in the utilization of each individual's skills and the profits obtained by each worker. The purpose of this study is to maximize profits based on task allocation according to worker abilities. This study uses the Hungarian method to solve the assignment problem by adding one dummy employee to equalize the number of workers and jobs. By creating a profit table and applying the steps of the Hungarian method, both manually and using the POM-QM for Windows V5 application, optimal assignment results were obtained with a total profit achieved in a week of IDR 2,325,000. These results indicate that efficient assignment management can increase profits and provide a fairer distribution of work.

ANALISIS RISIKO KEAMANAN SIBER DAN STRATEGI PERLINDUNGAN DATA PADA E-COMMERCE UMKM DI INDONESIA

2026-04-10T18:48:57+07:00

The rise of e-commerce has created significant opportunities for Micro, Small, and Medium Enterprises (MSMEs) to access a broader market. However, this digital age also brings considerable cybersecurity risks, including data leaks and cyberattacks. This study investigates cybersecurity risks in MSME e-commerce in Indonesia, evaluates their impact on consumer trust, and proposes practical solutions. Using a mixed-method approach that includes a literature review, interviews with MSME stakeholders, and case study analysis, this research identifies key challenges such as inadequate cybersecurity awareness and limited technological infrastructure. Findings indicate that implementing encryption technology, conducting cybersecurity training, and fostering partnerships with technology service providers can significantly enhance MSME data protection. The study contributes to both academic research and policy development in the field of cybersecurity for MSMEs.

IMPLEMENTASI METODE FUZZY LOGIC BERBASIS INTERNET OF THINGS PADA ALAT PENYIRAMAN OTOMATIS TANAMAN PEPAYA CALIFORNIA

2026-05-05T07:36:47+07:00

Watering is a crucial factor in California papaya plant maintenance. Soil moisture content is a major limiting factor in California papaya cultivation, where maintaining consistent moisture is crucial for optimal growth, flower formation, and fruit productivity. Soil moisture should not be too dry, as dry soil can slow the development of California papaya plants. Conversely, overwatering can cause California papaya plants to die due to excessive root absorption. This study aims to implement the Fuzzy Logic method in an Internet of Things-based automatic watering device for California papaya plants. Using the Fuzzy Logic method can make the agricultural system more effective and efficient. The results of this study were able to effectively monitor California papaya plants. The output generated by this device was able to display sensor readings on a 4x20 I2C LCD and displayed in the Blynk application. The results of soil moisture measurements under normal conditions were 20%, dry conditions 4%, and wet conditions 80%. The results of soil temperature measurements using the DS18B20 sensor had an average error of 1.56%. The average error of the soil pH sensor under normal conditions is 2.66%, under acidic soil conditions it is 4.65%, and under growing media with pH-enhancing fertilizer it is 2.56%. The water pump will turn on when the fuzzy logic system reads soil moisture in the dry (0%-40%), moist (40%-70%) and wet (70-80%) categories, and the pump will automatically turn off when it reaches the wet (70-80%) category.

IMPLEMENTASI METODE SIMPLE ADDITIVE WEIGHTING (SAW) UNTUK MENENTUKAN SISWA BERPRESTASI PADA SMK RHOUDHOTU TOLIBIN

2026-04-05T19:38:43+07:00

Determining outstanding students in school is a crucial process that requires objectivity and accuracy. Outstanding students are not only measured by academic grades, but also involve various aspects such as attitude, discipline, and participation in school activities. Seeing these conditions, it is necessary to have someone who can support decision-making for the selection of outstanding students. This study aims to implement the Simple Additive Weighting (SAW) method to determine outstanding students at SMK Rhoudhotu Tolibin. From the results of the calculations that have been carried out, it can be concluded that the application of the SAW method to determine outstanding students is based on 3 criteria, namely report card scores, attitudes/character and skills