Journal of Informatics Management and Information Technology

Sistem Pendukung Keputusan Pemilihan Tanaman Pertanian Berdasarkan Kondisi Lahan dan Iklim Menggunakan Metode AHP-TOPSIS

2025-12-20T20:28:48+07:00

The selection of crops that are suitable for land and climate conditions is an important factor in increasing agricultural productivity and resource utilization efficiency. This study aims to develop a decision support system (DSS) in the selection of food and horticultural crops based on local agroclimatic conditions using an integration of the Analytical Hierarchy Process (AHP) and Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) methods. The case study was conducted in Bantul Regency, Yogyakarta Special Region, by considering five main criteria, namely soil type, humidity, rainfall, air temperature, and altitude, as well as five alternative crops, namely rice, corn, soybeans, tomatoes, and chilies. The AHP method was used to determine the importance weight of each criterion based on expert assessment, while the TOPSIS method was used to rank alternative crops based on their suitability level. The results of the AHP calculation showed that soil type was the most influential criterion with a weight of 0.4301, followed by humidity, rainfall, altitude, and air temperature. Based on the TOPSIS analysis, rice plants obtained the highest preference value (C = 0.8688), so it is recommended as the most suitable plant for the agro-climatic conditions of Bantul Regency, while chili plants obtained the lowest preference value (C = 0.1311). These ranking results are in line with the real conditions and historical agricultural patterns in Bantul Regency, which is known as one of the rice production centers, thus indicating that the proposed DSS model is able to represent the agro-climatic conditions of the study area rationally and based on data. This research is expected to be the basis for the development of a more adaptive and applicable agricultural decision support system in supporting crop cultivation planning.

Analisis Warna dan Tipografi Aplikasi Siap Kerja menggunakan UCD Untuk Tingkat Kepuasan Green UI

2025-12-31T17:37:41+07:00

This study aims to analyze the impact of color, font type, and green interface design on user satisfaction in the Siap Kerja mobile application. The problem that prompted this study was the low level of user satisfaction due to the selection of colors that were uncomfortable for the eyes, font types that reduced readability, and interface designs that did not fully apply the principles of sustainability in the user experience (sustainable UI). In digital interface design, sustainability is not only related to broad environmental issues, but also includes energy efficiency and visual comfort when using the application. Before filling out the questionnaire, respondents were given a preview of the Siap Kerja application interface to assess the color elements, typography, and green interface design concept. The concept of green interface design in this study refers to the optimization of visual aspects, such as application design with dark mode, as well as the selection of visually efficient typography. This optimization not only helps reduce device power consumption but also improves user comfort and reduces eye strain. Therefore, sustainability is considered one of the characteristics of interface design, not a form of satisfaction in itself. The results of the study show that color, typography, and green interface design have a significant impact on user satisfaction, with an explanatory level of 0.84. These findings indicate that the application of sustainable UI principles can improve the quality of the user experience while supporting energy efficiency in the use of digital applications.

Pengembangan Media Pembelajaran Logika Boolean Berbasis Web Menggunakan Pyodide Dengan Pendekatan Prototyping Bagi Mahasiswa Teknik Informatika

2026-01-03T18:35:02+07:00

Boolean logic learning is a fundamental competency that must be mastered by Informatics Engineering students as a foundation for understanding digital computation and programming concepts. However, the presentation of theoretical materials often makes it difficult for students to visualize the relationship between binary inputs and logical operation outputs, which leads to a low level of conceptual understanding. This study aims to develop a web-based Boolean logic learning medium that integrates the Pyodide engine to provide interactive simulations directly within a browser environment. The application is designed to assist students in understanding Boolean logic operations through truth table visualization, binary input simulations, and mini-game features as learning exercises. The research method employs a prototyping approach consisting of needs analysis, system design, application implementation, and user evaluation stages. The evaluation was conducted through pilot testing involving five Informatics Engineering students from Universitas Pamulang to assess the application’s functionality, usability, and initial user acceptance as a learning medium. The results indicate that the application produces outputs that are consistent with Boolean logic truth tables and achieves a high level of user acceptance. These findings suggest that the developed learning medium has the potential to serve as an effective interactive learning tool in supporting students’ initial understanding of Boolean logic concepts prior to broader-scale testing.

Sistem Pendukung Keputusan Rekomendasi Lokasi Wisuda Menggunakan Metode MOORA

2026-01-27T16:53:16+07:00

In a university, mistakes often occur in choosing a good graduation location, therefore before holding a graduation ceremony at Budi Darma University, you must first determine where the right location is to hold the event, because determining the right location will minimize costs. Graduation is a ceremony of confirmation or inauguration for a student who has completed his education at a university or college. In this research, the aim is to build a decision support system (DSS). Which has a function as a tool to determine decision making in the process of selecting the location for the graduation ceremony to be held by Budi Darma University. Determination of the location of the graduation ceremony is also carried out with great attention to several aspects which are an important strategy that will be considered in determining the location of the graduation ceremony which is absolutely and very much needed. The Moora method is one of the Multi-Criteria decision making (MCMD). Is a method that requires statistical procedures for selecting the best alternative given. This method also produces a very suitable alternative by considering something good and profitable.

Pengelompokan Pola Interaksi Pengguna Media Sosial Menggunakan Algoritma K-Means untuk Pemetaan Aktivitas Online

2026-01-17T15:35:54+07:00

This study aims to cluster social media user interaction patterns in order to obtain a more structured and informative mapping of online activities. User activity on social media platforms is increasing and diverse, ranging from the frequency of uploads, the intensity of comments, the pattern of information dissemination, to responses to certain content. This complexity creates problems in understanding the characteristics of user behavior as a whole, especially when the resulting data is very large and unstructured. To address this challenge, this study applies the K-Means Clustering algorithm, one of the data mining methods that is effective in clustering data based on similar characteristics. The dataset used comes from user activities that include the number of posts, the number of likes, the number of comments, and the level of daily interactions. K-Means is used to divide the data into several clusters that represent the types of user activities, such as active, semi-active, and passive users. The results show that the K-Means algorithm is able to produce a clear and measurable mapping of online activities, with evaluation values ??using SSE and silhouette scores indicating optimal cluster formation. From the grouping process, Cluster 1 was obtained as passive users consisting of U001, U002, U005, U007, and U009 with a final centroid value of C1 of (0.13; 0.13; 0.10; 0.18), Cluster 2 as active users consisting of U003, U004, U006, and U010 with a final centroid value of C2 of (0.53; 0.55; 0.59; 0.49; 0.62), and Cluster 3 as very active users consisting only of U008 with a final centroid value of C3 of (1.00; 1.00; 1.00; 1.00).

Implementasi Data Mining Dalam Pengelompokan Perilaku Penggunaan Media Sosial Siswa SMA Menerapkan Algoritma K-Means

2026-01-20T16:50:39+07:00

The development of information and communication technology has encouraged the increasing use of social media among teenagers, especially high school students (SMA). Social media is not only used as a means of communication and entertainment, but also has the potential to influence students' learning behavior. Excessive use can reduce concentration and learning effectiveness, so analysis is needed to systematically identify patterns of social media usage behavior. This study aims to group the social media usage behavior of high school students using the K-Means Clustering algorithm. Data were obtained through a closed questionnaire with a numerical scale that includes three variables, namely the frequency of social media use, duration of use, and the number of social media platforms used. A total of 20 sample data were used to illustrate the calculation process. The analysis stages include data normalization using the Min-Max method, determining the number of clusters as many as three clusters (K = 3), calculating distances using Euclidean Distance, and iteratively updating the entroids. Based on the results of the K-Means algorithm calculations until reaching a convergent condition, the social media usage behavior of high school students was successfully grouped into three clusters, namely low usage with centroids (3.50; 1.25; 2.75), moderate usage with centroids (7.25; 3.25; 5.88), and high usage with centroids (12.25; 5.75; 8.88). These results indicate that the K-Means algorithm is effective in grouping students' social media usage behavior based on differences in access frequency, duration of use, and level of social media interaction.

Penerapan Sistem Aplikasi Hybrid untuk Optimalisasi Pengelolaan Sampah di Bank Sampah Desa

2026-01-20T16:41:32+07:00

As a result of the increased volume of waste not being matched by an effective management system, waste management in densely populated areas like Pondok Aren District, South Tangerang, remains a major problem. The concept of a waste bank in Pondok Karya Village is one solution, but the still-manual recording and transaction system often causes problems such as inaccurate data, limited information access, and slow administrative processes. To address this issue, a hybrid waste bank application was developed that can be accessed via web and Android devices. This research aims to design, implement, and evaluate a hybrid application to improve the efficiency, transparency, and community participation in managing a waste bank. Key features of the application include automatic payments, notifications, transaction data management, and periodic reports, which digitize the processes of recording, reporting, education, and communication between managers and the public. The application development process follows the Waterfall model of the Software Development Life Cycle (SDLC), which includes requirements analysis, system design, development, testing, implementation, and evaluation, and involves collaboration between the university, waste bank managers, and the community. The results of using this application show that it is able to increase the efficiency and transparency of waste bank management and encourage community participation in sustainable technology-based waste management.

Manajemen Bank Sampah Berbasis GIS untuk Ekonomi Sirkular: Analisis Bibliometrik dan Tinjauan Pustaka Sistemastis

2026-01-17T15:36:14+07:00

Although waste banks are crucial for a circular economy, waste management is often problematic due to a lack of spatial data and inefficient logistics. While the use of geographic information systems (GIS) has the potential to optimize the waste supply chain, there is limited comprehensive research linking GIS to waste banks. This means there is no clear strategic guidance on how to use technology to increase the economic value of waste. This study used the Bibliometric Analysis and Systematic Literature Review (SLR) method. The steps involved: extracting metadata from Scopus and Web of Science databases; identifying topic trends and clusters within the research network using VOSviewer; synthesizing selected literature to evaluate the effectiveness of GIS use; and formulating a technology integration model for waste bank operations. This research yields a model for system managers. To reduce operational costs, the proposed solution includes GIS-based strategic location determination and a model for optimizing transportation routes. The results will help users create a transparent spatial monitoring dashboard, which will accelerate the transition to a circular economy through smarter and more controlled waste bank management.

Perancangan Website E-Commerce Untuk Mendukung Digitalisasi Usaha Mikro Kecil dan Menengah Menggunakan Metode Waterfall

2025-12-31T17:36:28+07:00

The development of digital technology provides significant opportunities for Micro, Small, and Medium Enterprises (MSMEs) to expand their market reach through online platforms. However, most MSMEs in Lubuklinggau City still rely on conventional sales without an integrated e-commerce system, resulting in suboptimal processes for ordering, payment, and product management. This study aims to design and develop a web-based e-commerce platform to support the digitalization of MSMEs in Lubuklinggau City. The system was built using the Waterfall development method, which includes requirement analysis, system design, implementation, and testing. Laravel was implemented as the primary framework due to its robust MVC architecture and support for large-scale application development. The platform is also equipped with a Midtrans payment gateway for digital transactions, WhatsApp Gateway for notification services, and Gmail SMTP for account verification. Blackbox testing results indicate that all core system functions operate as expected, including product ordering, store management, checkout processes, digital wallet features, automatic refunds, and store status synchronization. The developed platform enables MSMEs to promote their products more efficiently, enhances customer trust through secure transactions, and contributes to accelerating digital transformation in Lubuklinggau City.

Klasifikasi Penyakit Tanaman Mangga Menggunakan Citra Daun Dengan Pendekatan Transfer Learning Efficientnet-B0

2025-12-31T17:37:52+07:00

Mango plant disease is one of the factors that can reduce the quality and productivity of the harvest. Manual identification of mango leaf diseases still relies on visual observation, potentially requiring a long time and producing inconsistent diagnoses. This study aims to develop a mango plant disease classification system based on leaf images using a transfer learning approach with the EfficientNet-B0 architecture. The dataset used consists of eight classes, namely seven types of mango leaf diseases and one class of healthy leaves. EfficientNet-B0 is used as a feature extractor with pre-trained weights from ImageNet, then custom layers are added in the form of Batch Normalization, Dense, and Dropout to adjust to classification needs. The training process was carried out for 10 epochs by dividing the data into training, validation, and test data. The test results show that the model achieves maximum performance on the dataset used, indicated by very high accuracy, precision, recall, and f1-score values ??across all classes. Visualization of individual image predictions also shows a prediction confidence level of 0.91 for one of the disease classes. While these results demonstrate the potential of EfficientNet-B0 in mango leaf disease classification, the very high performance achieved in a limited number of epochs indicates the need for further evaluation of the model's generalization capabilities.

Sistem Pendukung Keputusan Pemilihan Mahasiswa Berprestasi Menggunakan Metode MOORA dan MOOSRA

2026-02-02T17:26:12+07:00

Students are students who are studying or completing their education at the tertiary level. Efforts to identify students' talents and interests are crucial for improving human resources. One way to do this is by selecting high-achieving students. In addition to rewarding these high-achieving students, this also serves as motivation for other students to further develop their talents and interests. Efforts to select high-achieving students are still ineffective because the criteria for selecting high-achieving students are based on the assessments of lecturers during teaching. Meanwhile, many other criteria serve as references in selecting high-achieving students. To address this problem, a decision support system is needed to assist in the selection process. The methods used in selecting high-achieving students are the MOORA and MOOSRA methods. The results that can be found in calculating the best alternative as an outstanding student using the MOORA method are students named Septiaman with a value of 0.307. while in the MOOSRA method, the name of Septiaman has a value of 4.165. in the MOORA method, there are the same alternative values, namely Try Yanti and Vessy alwi, each of which has a value of 0.259. while in the MOOSRA method, the values ??of the two alternatives are different, making it easier to determine the best alternative.

Development of a Web Repository of ADDIE-Based Course Teaching Materials as an Institutional Digital Archive with ISO 25010 Evaluation

2025-12-31T17:38:52+07:00

The storage of course teaching materials in the Department of Informatics and Computer Engineering, Makassar State University, has so far been separate for each lecturer and semester-based, thus complicating the process of archiving, searching, and reusing teaching materials across semesters. This study aims to develop a web repository of course teaching materials as a permanent centralized storage medium and to evaluate the quality of the resulting system. The research method used is Research and Development (R&D) with the ADDIE (Analyze, Design, Develop, Implement, and Evaluate) development model. The results of system quality testing based on the ISO 25010 standard show that the functional suitability aspect obtained a feature completeness value of 1 or 100%, the usability aspect achieved a feasibility percentage of 94.3% with a very feasible category, and the reliability aspect showed a test success rate of 100%. The performance efficiency test obtained a Grade A with an average page load time of 1.7 seconds, while the portability, compatibility, and maintainability tests showed that the system can run well on various devices and environments. Security testing using URLVoid demonstrated that the system meets basic security requirements, namely being free from malware based on domain reputation scanning, although in-depth code security testing has not yet been conducted. Based on these results, the developed course material web repository is deemed suitable for use as an institutional digital archiving system to support effective and sustainable management of teaching materials.

Analisis Sentimen Program Makan Gratis Pada Media Sosial X Menggunakan Metode Naïve Bayes

2026-01-20T16:58:41+07:00

The Free Meal Program is a public policy aimed at improving students' nutritional needs. However, the program's implementation has generated diverse responses from the public. This study aims to analyze public sentiment in Medan Tuntungan District towards the Free Meal Program based on opinion data obtained from social media platform X. The methods used include text preprocessing, word weighting using Term Frequency–Inverse Document Frequency (TF-IDF), and sentiment classification using the Naïve Bayes algorithm. The research data was divided into training and test data with a ratio of 80% and 20%. The analysis results indicate that public sentiment is dominated by negative sentiment, generally related to food quality, portion adequacy, and program budget management. Model performance evaluation indicates that the Naïve Bayes algorithm is able to identify trends in public sentiment, although the accuracy obtained still shows limitations in classification performance. These findings provide an empirical overview of public perception of the Free Meal Program at the local level and serve as a basis for developing more adaptive sentiment analysis methods in future research.

Klasifikasi Minat Belanja Online pada TikTok Berdasarkan Konten Media Sosial Menggunakan Metode Naive Bayes

2026-01-23T11:08:28+07:00

The development of social media, especially TikTok, has driven changes in consumer behavior in online shopping through digital content and the TikTok Shop feature. This study aims to classify TikTok users' online shopping interests based on the type of social media content using the Naïve Bayes method. This study uses a quantitative approach with data mining methods on 100 data consisting of 50 data (50%) in the Interested category and 50 data (50%) in the Not Interested category. The types of content analyzed include Promotion, Product Review, Entertainment, Education, and Vlog. The results of the Naïve Bayes implementation show a prior probability value of P(Interested) = 0.5 and P(Not Interested) = 0.5. The conditional probability calculation produces a posterior value of 0.25 for Promotion and Product Review content, so they are classified as Interested. Conversely, Entertainment and Education content has a posterior value of 0.19, while Vlog content is 0.12, so it is classified as Not Interested. The final results showed that 2 of 5 content types (40%) influenced shopping interest, while 3 content types (60%) had no effect. Thus, the Naïve Bayes method is effective for classifying online shopping interest based on TikTok content type.

Classification of Student Graduation using The Rough Set Method at Public Elementary School

2026-01-20T16:56:33+07:00

Education is an important process in developing individual potential, including intellectual, emotional, social, and moral aspects. The student graduation rate is the main indicator of educational success at the elementary school level. However, Vocational High School Putra Anda Binjai faces challenges in determining student graduation due to inaccuracy in classification, which can impact the quality of education. This study implements the Rough Set method as an approach in classifying student graduation based on academic factors such as grades, attendance, behavior, and character. The Rough Set method is able to handle inaccurate and inconsistent data and find hidden patterns that can improve classification accuracy. This study uses student academic datasets to build a classification model that will be evaluated using accuracy and effectiveness measures. This study contributes to improving academic decision making and the quality of education in elementary schools through more accurate graduation classification.

An End-to-End Python Based Data Science Framework for Customer Transaction Big Data Analytics

2026-01-20T17:01:22+07:00

This study aims to address the problem of underutilized big data customer transactions by implementing a data science approach using the Python programming language. Many organizations accumulate large volumes of transaction data; however, these data often fail to generate strategic value due to the absence of systematic analytical models. The main problem examined in this research is how customer transaction big data can be processed and analyzed to extract meaningful insights that support data-driven business decision making. As a solution, this study applies a Python-based data science model that integrates data preprocessing, exploratory data analysis (EDA), and machine learning techniques to uncover patterns of customer behavior.The model used in this research is developed using Python and its data science ecosystem, including pandas and NumPy for data manipulation, matplotlib for data visualization, and scikit-learn for machine learning implementation. Customer transaction data are processed through several analytical stages, beginning with data cleaning and transformation, followed by the construction of behavioral variables using the Recency, Frequency, and Monetary (RFM) framework. Subsequently, a clustering model based on the K-Means algorithm is applied to segment customers according to their transaction characteristics. The results of the study show that the proposed data science model is effective in extracting insights from big data customer transactions. The clustering process successfully identifies distinct customer segments with different levels of activity and value contribution. The findings reveal three main customer groups: low-contribution customers, potential customers, and high-value customers. These results demonstrate that the implementation of data science using Python can transform raw transaction data into actionable knowledge that supports more targeted marketing strategies, improved customer retention, and enhanced strategic decision making.