Article Per Year (5 Year)
p-Index From 2021 - 2026
0.562
P-Index
This Author published in this journals
All Journal MATRIK : Jurnal Manajemen, Teknik Informatika, dan Rekayasa Komputer Jurnal Mantik
Makaruku, Yoakhina Nicole
Unknown Affiliation
Computer Science & IT Economics, Econometrics & Finance Languange, Linguistic, Communication & Media

Published : 3 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 3 Documents
Search

 1 
Classification of regional language diversity in the maluku region using decision trees Tomhisa, Ghyovanno Godlif; Latuny, Wilma; Makaruku, Yoakhina Nicole; Manuhuttu, Jermias Victor; Hawurubun, Hendri
Jurnal Mantik Vol. 9 No. 4 (2026): February: Manajemen, Teknologi Informatika dan Komunikasi (Mantik)
Publisher : Institute of Computer Science (IOCS)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35335/mantik.v9i4.6935

Abstract

Regional languages are an important part of cultural heritage that reflect the identity, values, and character of a community. In Maluku Province, there is a high degree of linguistic diversity because the region consists of many islands with different community characteristics. However, the passage of time, modernization, and population mobility have led to a decline in the number of speakers in some areas, threatening the extinction of a number of regional languages. This study aims to classify and visualize the diversity of regional languages in Maluku Province using the Decision Tree algorithm. This method was chosen because it is capable of recognizing patterns and relationships between variables, such as region, number of speakers, and language vitality. The research data was obtained from the compilation of the Language Agency and field observations, then processed using Python with the help of the pandas, scikit-learn, matplotlib, and Streamlit libraries to produce an interactive analytical dashboard. The results showed that regional languages on Seram Island, such as Tana, Alune, and Wemale, had higher vitality levels than languages in other regions. The Decision Tree model built was able to classify language status with an accuracy rate of 92%. The resulting visualization provided a clear picture of the actual condition of regional languages in Maluku and could be used as a basis for regional language preservation and development efforts by local governments.
Analysis of hotel visits in Ambon city using the naive bayes algorithm Doren, Henderina; Manuhutu, Jermias Victor; Makaruku, Yoakhina Nicole; Latuny, Wilma; Maimina, Apritiwi
Jurnal Mantik Vol. 9 No. 4 (2026): February: Manajemen, Teknologi Informatika dan Komunikasi (Mantik)
Publisher : Institute of Computer Science (IOCS)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35335/mantik.v9i4.6936

Abstract

The rapid growth of tourism in Ambon City has increased competition among accommodations, necessitating data-driven performance evaluations. Prospective tourists often struggle with unstructured online reviews, while hotel management requires precise insights for improvement. This study aims to systematically classify hotel performance in Ambon City using the Naïve Bayes Algorithm based on reviews from platforms like Agoda and TripAdvisor. Adopting a descriptive quantitative methodology, the study processes and labels performance data as "Good," "Poor," or "Very Good." Findings demonstrate that the Naïve Bayes model is highly effective, achieving 91% accuracy. Evaluation via a Confusion Matrix confirms the model's reliability in predicting majority categories, proving that ratings and reviews are strong satisfaction predictors. While the model faces minor challenges with the "Poor" minority category due to limited data, the study provides strategic value. It offers management guidance for targeted improvements and helps tourists make informed decisions, ultimately enhancing the competitiveness of Ambon’s hospitality industry
Enhancement of Supervised Learning Models for Intrusion Detection Through Mutual Information and Hyperparameter Tuning Jollyta, Deny; Makaruku, Yoakhina Nicole; Hajjah, Alyauma; Marlim, Yulvia Nora
MATRIK : Jurnal Manajemen, Teknik Informatika dan Rekayasa Komputer Vol. 25 No. 2 (2026)
Publisher : Universitas Bumigora

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30812/matrik.v25i2.5760

Abstract

Enhancing the performance of supervised learning algorithms through feature and hyperparameter testing remains challenging for users, particularly when detecting computer network intrusions. There are opportunities to assess whether a supervised learning algorithm performs optimally, depending on the number of features and the choice of hyperparameters. The purpose of this research is to enhance the network intrusion detection performance of three supervised learning algorithms, namely Support Vector Machine (SVM), eXtreme Gradient Boosting, and Random Forest, by using the Mutual Information feature selection approach and hyperparameter tuning. Mutual Information measures the dependency of features on the target. Features with high values are the most informative. Hyperparameters are not learned from the data; they are set before training begins. Hyperparameters are selected in accordance with the requirements of the three algorithms via iterative training and testing on the NSL-KDD dataset. The dataset was split into 80:20, 70:30, and 60:40. The results showed that the fifteen features with the highest mutual information were identified and trained on the data using appropriate hyperparameters. By splitting the data in an 80:20 ratio, the accuracy of Support Vector Machine reached its maximum, increasing from 90% to 98%. In contrast, eXtreme Gradient Boosting and Random Forest reached their maximum, increasing from 97% and 98% to 100%, respectively. The study’s findings advance our understanding of how algorithm performance depends on feature and hyperparameter selection.
Co-Authors Alyauma Hajjah Deny Jollyta Doren, Henderina Hawurubun, Hendri Latuny, Wilma Maimina, Apritiwi Manuhuttu, Jermias Victor Manuhutu, Jermias Victor Marlim, Yulvia Nora Tomhisa, Ghyovanno Godlif