Jurnal Komtika (Komputasi dan Informatika)
Aims Jurnal Komtika (Komputasi dan Informatika) is a scientific journal published by the Faculty of Engineering, Universitas Muhammadiyah Magelang and is Accredited by the Ministry for Research, Technology, and Higher Education (RISTEKDIKTI)(No:200/M/KPT/2020). It is a medium for researchers, academics, and practitioners interested in Computer Science and wish to channel their thoughts and findings. Our concept of Informatics includes technologies of information and communication as well as results of research, critical, and comprehensive scientific study which are relevant and current issues covered by the journals. Jurnal Komtika publishes regular research articles. We encourage researchers to publish their theoretical and empirical results in as much detail as possible. For theoretical papers, full details of proofs must be provided so that the results can be checked; for experimental papers, full experimental details must be given so that the results can be reproduced. Additionally, electronic files or software regarding the full details of the calculations, experimental procedure, etc., can be deposited along with the publication as “Supplementary Material”. Scope Jurnal Komputasi dan Informatika (Komtika) focuses on various issues, but not limited in the field of: Software Development: Software development process, Requirements analysis, Software design, Software construction, Software deployment, Software maintenance, Programming team, Open-source model Mathematics of Computing: Discrete mathematics, Mathematical software, Information theory Theory of computation: Model of computation, Computational complexity Human Computer Interaction: Interaction design, Social computing, Ubiquitous computing, Visualization, Accessibility, User Interface Study, User Experience Study Applied Computing: E-commerce, Enterprise software, Electronic publishing, Cyberwarfare, Electronic voting, Video game, Word processing, Operations research, Educational technology, Document management. Machine Learning: upervised learning, Unsupervised learning, Reinforcement learning, Multi-task learning Graphics: Animation, Rendering, Image manipulation, Graphics processing unit, Mixed reality, Virtual reality, Image compression, Solid modeling Information System: Database management system, Information storage systems, Enterprise information system, Social information systems, Geographic information system, Decision support system, Process control system, Multimedia information system, Data mining, Digital library, Computing platform, Digital marketing, World Wide Web, Information retrieval
Articles
144 Documents
<![CDATA[Analisis Efektivitas Dua Jenis Gaya Prompt dalam Model LLM Berbasis RAG ]]>
<![CDATA[Rizky, Muhammad Ainur]]>
<![CDATA[ Jurnal Komtika (Komputasi dan Informatika) Vol 9 No 1 (2025) ]]>
Publisher : <![CDATA[Universitas Muhammadiyah Magelang ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.31603/komtika.v9i1.13488
<![CDATA[This study aims to analyse the effectiveness of two prompt styles, namely guided prompt and free prompt, in influencing the quality of answers generated by a Retrieval-Augmented Generation (RAG)-based Large Language Model (LLM) system using the META-Llama 3 model. The system is designed to answer questions based on reference documents stored in vector form through an embedding process. The research was conducted using questions formed in two versions of the prompt style, and the answer results were evaluated using two metrics ROUGE and BERTScore. The results showed that guided prompts resulted in higher scores on ROUGE-1, ROUGE-2, and ROUGE-L metrics reflecting a better level of precision and lexical agreement. Meanwhile, the BERTScore between the two prompt styles did not show any significant difference, meaning that in terms of meaning or semantic similarity, they provided relatively equivalent results. These findings suggest that prompt design has a real impact on the structure and precision of answers.]]>
<![CDATA[Web Game Implementasi Metode Agile dalam Pembuatan Sistem Game Edukatif Berbasis Web untuk Pembelajaran Bahasa Inggris Tingkat Sekolat Dasar ]]>
<![CDATA[Pratiwi, Ayu Okta]]>;
<![CDATA[Qisthiano, M Riski]]>;
<![CDATA[Aulia, Nanda Aftaa]]>
<![CDATA[ Jurnal Komtika (Komputasi dan Informatika) Vol 9 No 1 (2025) ]]>
Publisher : <![CDATA[Universitas Muhammadiyah Magelang ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.31603/komtika.v9i1.13495
<![CDATA[This research aims to develop a web-based educational game system aimed at supporting the English language learning process at the elementary school level. The main problem raised is the low interest and motivation of students in learning English through conventional learning methods which tend to be monotonous. To overcome this, a technology-based approach is used by applying Agile methods in the system development process. The Agile method was chosen because it is flexible and allows system development to be carried out gradually and repeatedly according to user needs. The development process includes planning, design, implementation, testing and evaluation stages. The system developed consists of several main features, such as a login page, user dashboard, and game page which includes listening, vocabulary and sentence material. The results of this research show that the system built is able to provide a more interesting, interactive and effective learning experience for elementary school students. Thus, the application of web-based educational game technology can be an alternative solution that supports improving the quality of English learning]]>
<![CDATA[User Experience Prototipe High-Fidelity Preschool Assessment dengan Pendekatan Child-Centered Design ]]>
<![CDATA[Wulandari, Ika Arthalia]]>;
<![CDATA[Pujianto, Pujianto]]>;
<![CDATA[Octavia, Rahma]]>;
<![CDATA[Clarisa, Nadila Dwi]]>;
<![CDATA[Kusuma, Deryzal Prio Dwi]]>
<![CDATA[ Jurnal Komtika (Komputasi dan Informatika) Vol 9 No 1 (2025) ]]>
Publisher : <![CDATA[Universitas Muhammadiyah Magelang ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.31603/komtika.v9i1.13517
<![CDATA[Every child is unique, showcasing individual personalities, preferences, and skills from an early age. Therefore, families, educators, and caregivers need to monitor children's development to ensure they meet physical, emotional, and cognitive milestones appropriate to their age. Preschool assessment is critical in identifying developmental progress across domains such as moral and religious values, motor skills, mental abilities, language, socio-emotional skills, and artistic expression. However, limited parental knowledge and young children's communication barriers often hinder practical assessment. This study aims to develop and model the user interface of a Preschool Assessment application using the Child-Centered Design (CCD) approach, which positions children at the heart of the system design process. CCD incorporates children's characteristics through indirect engagement facilitated by the involvement of parents and teachers. The resulting interface prototype was evaluated using the System Usability Scale (SUS), with participation from 20 children and 15 parents or teachers. The SUS scores averaged 86.25 from children and 84.17 from parents/teachers, categorized as "Excellent." These results indicate that the interface achieved a high level of usability and is well-aligned with the needs and characteristics of preschool-aged users]]>
<![CDATA[Prediksi Curah Hujan Di Kabupaten Bogor Menggunakan Long Short-Term Memory Dan Gemma 2 ]]>
<![CDATA[Wijaya, Indra]]>;
<![CDATA[Herlawati, Herlawati]]>;
<![CDATA[Sari, Rafika]]>
<![CDATA[ Jurnal Komtika (Komputasi dan Informatika) Vol 9 No 1 (2025) ]]>
Publisher : <![CDATA[Universitas Muhammadiyah Magelang ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.31603/komtika.v9i1.13639
<![CDATA[Bogor Regency is an area that often experiences prolonged rainfall, especially during the rainy season. High rainfall causes problems such as floods and landslides. Therefore, accurate rainfall prediction is important for various needs, especially in disaster mitigation. This study aims to implement the Long Short-Term Memory (LSTM) algorithm as a model for prediction of historical rainfall data and use the Large Language Model (LLM) GEMMA 2 to provide interpretation of prediction results and recommendations based on the prediction results. The methods used include data collection from the BMKG online data website totaling 1804 data, data pre-processing, model building, model performance evaluation, and interpretation of results using LLM. The results of this study show that LSTM is able to produce the best performance by showing MSE 201.92 mm², Root Mean Square Error (RMSE) of 14.21 mm. the RMSE value shows an average error of 14.21 mm. In addition, the interpretation provided by LLM GEEMA 2 to help understand the prediction and provide practical recommendations for disaster mitigation due to rainfall.]]>
<![CDATA[Implementasi Support Vector Machine dan Resampling dalam Analisis Ulasan Pengguna Google Maps ]]>
<![CDATA[Khultsum, Umi]]>;
<![CDATA[Rahmawati, Eka]]>;
<![CDATA[Rahmawati, Annida]]>;
<![CDATA[Annajib, Barra Rifki]]>;
<![CDATA[Anggita, Christina Yuli]]>
<![CDATA[ Jurnal Komtika (Komputasi dan Informatika) Vol 9 No 2 (2025) ]]>
Publisher : <![CDATA[Universitas Muhammadiyah Magelang ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.31603/komtika.v9i2.14813
<![CDATA[The development of information technology has driven the increasing use of digital services such as Google Maps, which functions not only as a navigation tool but also as a platform for users to provide reviews. These reviews serve as an important data source for sentiment analysis; however, they are often unstructured and contain noise. This study aims to conduct sentiment analysis using the Support Vector Machine (SVM) model with the application of resampling techniques to address data imbalance issues in user reviews of the Google Maps application. A total of 1,000 recent reviews were collected through a scraping process, followed by data cleaning (lowercasing, stopwords removal, stemming, and lemmatization) and data preprocessing. The SVM model combined with resampling techniques was then implemented and evaluated using accuracy, precision, and recall metrics. The results indicate that the SVM model achieved an accuracy of 81%, with a weighted average precision of 0.79, recall of 0.81, and F1-score of 0.76. These findings demonstrate that applying resampling techniques to SVM yields good performance in sentiment classification. The study is expected to contribute to the development of sentiment analysis methods using the SVM model with resampling in the context of Google Maps reviews.]]>
<![CDATA[Desain Sistem Gamifikasi Digital Berbasis Octalysis dan MDA Framework untuk Promosi Pariwisata Kota Surakarta ]]>
<![CDATA[Agustina, Candra]]>;
<![CDATA[Rahmawati, Eka]]>;
<![CDATA[Permata, Afifta Ilham]]>;
<![CDATA[Laily, Isnaini Mufidatul]]>
<![CDATA[ Jurnal Komtika (Komputasi dan Informatika) Vol 9 No 2 (2025) ]]>
Publisher : <![CDATA[Universitas Muhammadiyah Magelang ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.31603/komtika.v9i2.14820
<![CDATA[Tourism plays a strategic role in driving local economic growth and preserving culture. However, the City of Surakarta still faces challenges such as the low length of stay of tourists and the lack of connectivity between destinations. This study aims to design a digital gamification strategy as an innovative approach to enhance the competitiveness of regional tourism. The research method used is mixed methods, combining qualitative and quantitative approaches. Data were collected through field observations, in-depth interviews with tourism stakeholders, surveys distributed to tourists, and trials of web- or mobile-based gamification applications. Qualitative data were analyzed using a thematic approach, while quantitative data were examined using descriptive and inferential statistics. The theoretical foundations applied are the Octalysis Framework and the MDA Framework (Mechanics–Dynamics–Aesthetics) to design game elements such as points, badges, challenges, and leaderboards in tourism promotion. The expected outcome is the development of a contextual and applicable digital gamification strategy model that can increase tourist engagement, extend the length of stay, and more evenly distribute economic benefits across the tourism ecosystem. This research contributes both academically and practically, serving as a guideline for local governments and tourism industry players to adopt interactive and sustainable digital strategies.]]>
<![CDATA[Pendekatan Hibrida Statistik dan Machine Learning untuk Peramalan Jumlah Kunjungan Turis ]]>
<![CDATA[Leidiyana, Henny]]>;
<![CDATA[Nurajizah, Siti]]>
<![CDATA[ Jurnal Komtika (Komputasi dan Informatika) Vol 9 No 2 (2025) ]]>
Publisher : <![CDATA[Universitas Muhammadiyah Magelang ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.31603/komtika.v9i2.14909
<![CDATA[Tourist arrival forecasting is a crucial aspect of planning and decision-making in the tourism sector. Accurate predictions are essential to anticipate surges or declines in visitor numbers, design effective marketing strategies, and manage resources efficiently. This study proposes a hybrid forecasting approach that integrates traditional statistical methods with machine learning algorithms to improve the accuracy of tourist arrival forecasts. Five forecasting models are implemented: ARIMA as a representative of traditional statistical models; Random Forest and Extreme Gradient Boosting (XGBoost) as machine learning models; a simple hybrid model, which combines ARIMA and XGBoost predictions through simple averaging; a weighted hybrid model, which merges the two models using performance-based weights; and a stacking hybrid model, which utilizes a meta-model to optimize prediction combinations. Given that the dataset exhibits significant pattern changes, or structural breaks, particularly during the COVID-19 pandemic, this study employs a rolling window backtesting approach for model evaluation. This method allows the models to be tested progressively across normal, crisis, and recovery periods, providing a realistic assessment of their performance under dynamic conditions. Model performance is evaluated using three key metrics: RMSE, MAE, dan MAPE. The results demonstrate that the stacking hybrid model consistently achieves the lowest RMSE across all test periods, highlighting its ability to capture complex trends and extreme fluctuations caused by COVID-19 Keywords: Rolling Window Backtesting, Weighted Hybrid, Weighted Hybrid.]]>
<![CDATA[Perbandingan Metode Reduksi Noise pada Citra Digital Berbasis Website ]]>
<![CDATA[Salsabilla, Dea]]>;
<![CDATA[Wahyusari, Retno]]>
<![CDATA[ Jurnal Komtika (Komputasi dan Informatika) Vol 9 No 2 (2025) ]]>
Publisher : <![CDATA[Universitas Muhammadiyah Magelang ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.31603/komtika.v9i2.14966
<![CDATA[Citra digital memiliki peran penting dalam penyampaian informasi visual, namun kualitasnya sering menurun akibat gangguan berupa noise. Penelitian ini membahas tiga jenis noise utama, yaitu salt and pepper, gaussian, dan speckle, yang direduksi menggunakan tiga metode filter, yaitu median, gaussian, dan bilateral. Pengujian dilakukan dengan menerapkan setiap filter terhadap citra uji yang terkontaminasi berbagai jenis noise untuk mengevaluasi performa berdasarkan nilai Mean Squared Error (MSE) dan Peak Signal-to-Noise Ratio (PSNR). Hasil menunjukkan bahwa filter median secara konsisten memberikan performa terbaik pada ketiga jenis noise, dengan nilai MSE terendah sebesar 7,007 dan PSNR tertinggi 39,675 dB pada noise salt and pepper, MSE 72,046 dan PSNR 29,554 dB pada noise gaussian, serta MSE 60,917 dan PSNR 30,283 dB pada noise speckle. Sementara itu, filter gaussian dan bilateral menghasilkan nilai yang relatif dekat, namun tidak melampaui performa filter median. Kombinasi beberapa filter juga tidak selalu meningkatkan kualitas citra secara signifikan. Dengan demikian, dapat disimpulkan bahwa filter median merupakan metode reduksi noise paling efektif secara umum dalam mempertahankan kualitas citra digital terhadap berbagai jenis noise.]]>
<![CDATA[Analisis Sentimen Ulasan Pengguna Indonesia terhadap Platform Pembelajaran Digital Ruangguru Menggunakan Algoritma Leksikal Multilingual ]]>
<![CDATA[Rullyana, Gema]]>;
<![CDATA[Triandari, Rizki]]>
<![CDATA[ Jurnal Komtika (Komputasi dan Informatika) Vol 9 No 2 (2025) ]]>
Publisher : <![CDATA[Universitas Muhammadiyah Magelang ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.31603/komtika.v9i2.15110
<![CDATA[Penelitian ini bertujuan untuk mengidentifikasi sentimen pengguna terhadap Ruangguru, salah satu platform pembelajaran digital paling populer di Indonesia. Metode yang digunakan bersifat kualitatif dengan pendekatan analisis sentimen menggunakan Orange Data Mining. Data yang dianalisis terdiri dari 1.913 ulasan pengguna aplikasi Ruangguru yang dikumpulkan dari Google Play Store dalam rentang waktu 1 Januari 2024 hingga 1 Januari 2025. Proses analisis mencakup tahapan praproses, analisis frekuensi kata, visualisasi, serta klasifikasi berdasarkan polaritas sentimen. Kata-kata yang paling sering muncul antara lain “bagus”, “belajar”, dan “aplikasi”, yang menunjukkan fokus pengguna pada kinerja aplikasi dan pengalaman belajar. Hasil penelitian menunjukkan bahwa 1.091 ulasan (57,02%) diklasifikasikan sebagai positif, mencerminkan kepuasan terhadap fitur, kualitas konten, dan kemudahan penggunaan. Sementara itu, 679 ulasan (35,49%) bersifat netral, dan hanya 143 ulasan (7,47%) bersifat negatif. Visualisasi word cloud, scatter plot, dan histogram sentimen memperkuat temuan tersebut, dengan distribusi emosi yang didominasi oleh joy dan surprise. Temuan ini menyiratkan bahwa mayoritas pengguna memiliki pengalaman yang positif secara kognitif maupun emosional saat menggunakan aplikasi Ruangguru. Implikasi dari temuan ini menggarisbawahi pentingnya bagi pengembang aplikasi pembelajaran digital untuk mempriotaskan optimalisasi performa teknis dan peningkatan fitur interaktif berbasis pengalaman pengguna. Hal tersebut tidak hanya krusial untuk menjaga tingkat kepuasan pengguna yang telah terbentuk, tetapi juga esensial dalam membangun retensi dan loyalitas jangka panjang dalam ekosistem pembelajaran digital yang semakin kompetitif.]]>
<![CDATA[A Comparative Analysis of Univariate and Multivariate LSTM Models for Nokia (NOK) Stock Price Prediction ]]>
<![CDATA[Saputra, Roni]]>;
<![CDATA[Martanto, Martanto]]>;
<![CDATA[Dana, Raditya Danar]]>
<![CDATA[ Jurnal Komtika (Komputasi dan Informatika) Vol 9 No 2 (2025) ]]>
Publisher : <![CDATA[Universitas Muhammadiyah Magelang ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.31603/komtika.v9i2.15152
<![CDATA[Predicting stock prices is a challenging yet crucial task in financial markets. This research aims to compare the performance of two Long Short-Term Memory (LSTM) neural network models for forecasting the closing price of Nokia Corporation (NOK) stock: a univariate model using only historical closing prices and a multivariate model incorporating open, high, low, close, and volume (OHLCV) data. Utilizing historical daily data from 2015 to 2025, both models were trained to predict the next day's price based on the previous 60 days. The models' accuracy was rigorously evaluated using three key metrics: Mean Absolute Error (MAE), Root Mean Square Error (RMSE), and Mean Absolute Percentage Error (MAPE). The findings revealed a decisive outcome. The univariate LSTM model consistently outperformed its multivariate counterpart across all evaluation metrics. It achieved an MAE of 0.0591, an RMSE of 0.0887, and a MAPE of 1.39%, while the multivariate model recorded higher values of 0.0623, 0.0934, and 1.45%, respectively. This study concludes that for NOK stock prediction, a simpler model with fewer features proved to be more effective. The additional data points in the multivariate model did not enhance predictive accuracy and may have introduced noise, suggesting that the historical pattern of closing prices alone is a more powerful predictor for this particular asset.]]>
