Article Per Year (5 Year)
p-Index From 2021 - 2026
0.23
P-Index
This Author published in this journals
All Journal TELKOMNIKA (Telecommunication Computing Electronics and Control) Indonesian Journal of Electrical Engineering and Computer Science
Arif Nurwidyantoro
Universitas Gadjah Mada
Computer Science & IT

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

 1 
Single document keywords extraction in Bahasa Indonesia using phrase chunking I Nyoman Prayana Trisna; Arif Nurwidyantoro
TELKOMNIKA (Telecommunication Computing Electronics and Control) Vol 18, No 4: August 2020
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12928/telkomnika.v18i4.14389

Abstract

Keywords help readers to understand the idea of a document quickly. Unfortunately, considerable time and effort are often needed to come up with a good set of keywords manually. This research focused on generating keywords from a document automatically using phrase chunking. Firstly, we collected part of speech patterns from a collection of documents. Secondly, we used those patterns to extract candidate keywords from the abstract and the content of a document. Finally, keywords are selected from the candidates based on the number of words in the keyword phrases and some scenarios involving candidate reduction and sorting. We evaluated the result of each scenario using precision, recall, and F-measure. The experiment results show: i) shorter-phrase keywords with string reduction extracted from the abstract and sorted by frequency provides the highest score, ii) in every proposed scenario, extracting keywords using the abstract always presents a better result, iii) using shorter-phrase patterns in keywords extraction gives better score in comparison to using all phrase patterns, iv) sorting scenarios based on the multiplication of candidate frequencies and the weight of the phrase patterns offer better results.
Evaluating oversampling methods for imbalanced Arabic dialect identification Maulana Ihsan Ahmad; Aina Musdholifah; Arif Nurwidyantoro
Indonesian Journal of Electrical Engineering and Computer Science Vol 43, No 1: July 2026
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v43.i1.pp259-270

Abstract

This study investigates whether oversampling is a reliable solution for severe class imbalance in Arabic dialect identification. Using the Shami Corpus as a controlled testbed, we demonstrate that conventional oversampling often fails in high-dimensional sparse text spaces, but density based cluster filtering can effectively resolve this. We conduct a comparative evaluation of SMOTE, clustering-guided variants (ASTRA-SMOTE and SMOTE-RADIANT), and a cost-sensitive ClassWeight approach under an identical 5,644-dimensional feature-engineering pipeline using LightGBM and XGBoost. On the held-out test set, standard SMOTE and class weighting frequently distorted decision boundaries, yielding inconsistent gains across models. In contrast, SMOTE-RADIANT yields a statistically significant macro-F1 improvement for LightGBM (0.8539 vs. 0.8526 on the original data) with a large effect size (r = 0.511), successfully rescuing minority dialects without degrading the majority class. These findings suggest that while oversampling is not universally reliable in sparse text spaces, coupling it with density-based noise neutralization (RADIANT) provides a robust and interpretable alternative to deep learning models. This study provides methodological clarity and reproducible guidance for fair and inclusive Arabic NLP systems.
Co-Authors Aina Musdholifah I Nyoman Prayana Trisna Maulana Ihsan Ahmad