Dwiza Riana
Nusamandiri University

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

Found 3 Documents
Search

WORD2VEC OPTIMALIZATION USING TRANSFER LEARNING IN INDONESIAN LANGUAGE FOR HIGHER EDUCATION Dwiza Riana; Sri Hadianti; Herdian Tohir; Jarwadi Jarwadi; Tjaturningsih Rosdiana; Evi Sopandi; Dinar Ajeng Kristiyanti
JITK (Jurnal Ilmu Pengetahuan dan Teknologi Komputer) Vol. 11 No. 2 (2025): JITK Issue November 2025
Publisher : LPPM Nusa Mandiri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33480/jitk.v11i2.6051

Abstract

Natural language processing (NLP) in Indonesian faces challenges due to limited linguistic resources, particularly in developing optimal word embedding models. This study optimizes the Word2Vec model for Indonesian in higher education contexts by leveraging transfer learning and lexicon expansion. Using a dataset of 4,463 higher education related tweets consisting of positive and negative sentiment categories, the proposed NewWord2Vec model combined with a Support Vector Machine (SVM) classifier achieved a 4% improvement in word detection accuracy compared to the standard Word2Vec. This enhancement demonstrates better performance in capturing linguistic nuances and sentiment orientation in Indonesian text. However, the model’s applicability remains limited to higher education terminology, and potential biases from transfer learning must be addressed. Future research should expand the dataset to diverse domains and refine the transfer learning process to better capture contextual variations in Indonesian. These findings contribute to advancing NLP applications in Indonesian, particularly for automated assessment systems, recommendation tools, and academic decision-making processes
PENERAPAN K-MEANS DAN K-MEDOIDS BERBASIS RFM PADA SEGMENTASI PELANGGAN DI MASA PANDEMI COVID-19 Sri Watmah; Dwiza Riana; Rachmawati Darma Astuti
INTI Nusa Mandiri Vol. 18 No. 2 (2024): INTI Periode Februari 2024
Publisher : Lembaga Penelitian dan Pengabdian Pada Masyarakat

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33480/inti.v18i2.4963

Abstract

The outbreak of the CORONA virus in Indonesia in early March 2020 has created unrest, especially in the business world. The impact caused some small and medium-sized businesses to go out of business, so the right marketing strategy is needed to maintain and increase customer loyalty. The purpose of this research is to segment PT Megadaya Maju Selaras' customers based on their characteristics by comparing the RFM-based K-Means and K-Medoids algorithms as attributes in the research. The dataset used comes from the purchase transaction data of PT Megadaya Maju Selaras customers. Experiments in this study used the CRISP-DM model. The results showed that the K-Means algorithm has a smaller Davies Bouldin Index (DBI) value than K-Medoids, meaning that the K-Means method is the right method for this research. With the K-Means method, the overall data shows the optimal k in cluster 4 with a DBI value of 0.286, the data before the pandemic shows the optimal k value in cluster 2 with a DBI value of 0.299, after the pandemic shows the optimal k in cluster 5 with a DBI value of 0.278. The overall data is divided into 4 segments, namely superstar, typical customer, occational customer and dormant customer. Data before the pandemic is divided into 2 segments, namely typical customers and superstars. Meanwhile, after the pandemic is divided into 5 segments, namely typical customer, occational customer, golden customer, dormant customer and superstar. With this research, PT Megadaya Maju Selaras can provide the right service for each customer group.
BEMD-Based Color–Texture Feature Fusion with Image Sharpening for Multiclass Huanglongbing Severity Classification Rachmat Adi Purnama; Dwiza Riana; Mochamad Wahyudi; Sumanto
Journal of Information System and Informatics Vol 8 No 5 (2026): October
Publisher : Asosiasi Doktor Sistem Informasi Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.63158/journalisi.v8i5.1867

Abstract

Huanglongbing (HLB), or citrus greening disease, is one of the most destructive citrus diseases worldwide. Its symptoms often resemble nutrient deficiencies, making severity assessment difficult and subjective. This study proposes a color-texture feature fusion method to classify citrus leaf images into four HLB severity classes: healthy, mild, moderate, and severe. A dataset of 1,000 citrus leaf images from Sumanto et al. (2023), comprising 250 images per class, was used. HLB infection was validated using PCR/qPCR analysis, while severity annotations followed the original labeling protocol. Images were sharpened using a standard deviation of 0.1 and decomposed using Bidimensional Empirical Mode Decomposition (BEMD) into IMF1, IMF2, IMF3, and residue components to capture multiscale texture information. Color and texture features were fused and classified using Support Vector Machine (SVM), k-Nearest Neighbor (KNN), Random Forest (RF), and Neural Network (NN). Performance was evaluated using stratified k-fold cross-validation with out-of-fold predictions. BEMD with Color Fusion achieved the best SVM performance, with accuracy, precision, recall, and F1-score of 0.93 and computation time of 1.24 seconds. It outperformed Basic BEMD and BEMD Fusion Baseline, with accuracies of 0.77 and 0.89. These results demonstrate improved multiclass HLB severity classification, although independent field validation is required before practical deployment.