Claim Missing Document
Check
Articles

Found 35 Documents
Search

Peningkatan Loyalitas Pelanggan Melalui Integrasi Digital Marketing dan Desain Kemasan Produk Berbasis Behavioral Consumer Insights Pada UMKM Ifriza, Yahya Nur; Efrilianda, Devi Ajeng; Mandaya, Yusuf Wisnu; Alamsyah, Alamsyah
Jurnal Abdi Negeri Vol 2 No 2 (2024): September 2024
Publisher : Informa Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.63350/jan.v2i2.19

Abstract

Customer loyalty is an important element that determines the long-term success of MSMEs, especially in the midst of increasingly fierce market competition. Previous research shows that digital marketing and attractive packaging design play an important role in increasing customer loyalty and attracting new consumers emphasize that digital-based marketing strategies enable small and medium businesses to reach a wider market at low costs, while research by [3] shows that consumer behavior-based packaging design can increase consumer appeal and trust. Based on these results, this service program aims to integrate digital marketing strategies and packaging design based on behavioral consumer insights in 15 MSMEs in the culinary and crafts sectors. The results of the service showed an increase in MSMEs' understanding of digital marketing from 30% to 85% after the training. In addition, assistance with packaging design resulted in an increase in product attractiveness from 25% to 78%. Customer loyalty also increased significantly, with 68% of customers making repeat purchases after implementing the new strategy. This program supports previous research which confirms that the integration of digital marketing strategies and packaging design based on consumer behavior can increase MSME customer loyalty and competitiveness in the market.
Transformasi Digital Komunitas Abrasea Indonesia untuk Penguatan Peran Konservasi Pesisir di Jawa Tengah Sanusi, Ratna Nur Mustika; Ifriza, Yahya Nur; Febriyanto, Hendra
Jurnal Abdi Negeri Vol 3 No 2 (2025): September 2025
Publisher : Informa Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.63350/jan.v3i2.25

Abstract

Coastal abrasion in Central Java seriously threatens social, economic, and environmental sustainability. In response to this urgency, the Abrasea Indonesia Community was established as a new initiative for community-based conservation. However, as a newly formed organization, the effectiveness of its outreach programs and communication remains limited due to the absence of a structured digital platform. Therefore, this community service initiative aims to transform the community's operations by developing the digital platform abrasea.org as a hub for centralized information and increased public participation. The method employed is a participatory approach that actively involves community members in the planning and development of the platform, combined with quantitative and qualitative approaches to measure its success. The results show that within three months after its launch, the platform successfully increased website visitors by 75% and mobilized 80 new volunteers through online registration. This outcome strengthens institutional capacity and shifts the community's social behavior in organizing and publicizing activities. Thus, the digital platform has proven effective as a catalyst for expanding outreach and reinforcing the role of the Abrasea Indonesia Community in creating more sustainable conservation impacts since its inception.  
Strengthening Javanese literature material through the Novaja.id application as a form of Javanese cultural preservation Fateah, Nur; Subhan, Subhan; Ifriza, Yahya Nur; Ninsiana, Widhiya
Diglosia: Jurnal Kajian Bahasa, Sastra, dan Pengajarannya Vol 8 No 4 (2025)
Publisher : Universitas Mulawarman

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30872/diglosia.v8i4.1319

Abstract

The preservation of regional languages, including Javanese, increasingly requires digital innovations that can support literacy development and sustain readers’ engagement. However, existing digital platforms for Javanese literary access often lack systematic development frameworks and user-centered design features, limiting their effectiveness and long-term usability. Responding to this gap, this study develops the Novaja.id Javanese Novel Library application through the integration of the System Development Life Cycle (SDLC) and User-Centered Design (UCD) methodologies. The research began with a user needs analysis conducted through surveys and in-depth interviews, which informed the design of an intuitive interface and optimized user experience. A prototype was subsequently tested through usability evaluations, and user feedback was incorporated into iterative refinements. The findings show that the final application meets user needs effectively, demonstrating high navigation ease, satisfactory feature performance, and stable and secure functionality. These outcomes indicate that combining SDLC and UCD enhances application quality and usability. Overall, Novaja.id has strong potential to expand access to Javanese literary works and contribute to Javanese language literacy and cultural preservation.
Optimization CatBoost using GridSearchCV for Sentiment Analysis Customer Reviews in Digital Transportation Industry Ifriza, Yahya Nur; Sanusi, Ratna Nur Mustika; Febriyanto, Hendra; Kamaruddin, Azlina
TIERS Information Technology Journal Vol. 6 No. 2 (2025)
Publisher : Universitas Pendidikan Nasional

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.38043/tiers.v6i2.7201

Abstract

The rapid expansion of ride-hailing services has generated a massive volume of user feedback, making automated sentiment analysis essential for understanding customer satisfaction. This study aims to classify public sentiment towards the Uber application into positive, neutral, and negative categories using the CatBoost algorithm, a gradient boosting method prioritized for its Ordered Boosting mechanism, which effectively prevents overfitting and enhances the model's generalization capabilities. Despite the use of TF-IDF for numerical text representation, CatBoost is selected for its superior performance on heterogeneous datasets compared to other boosting frameworks like XGBoost and LightGBM. The dataset comprises customer reviews collected 12.000 from the Google Play Store between January and March 2024 using web scraping techniques upload in Kaggle. The data underwent rigorous preprocessing, including lemmatization and TF-IDF vectorization, to structure the textual features, to maximize model performance, hyperparameter optimization was conducted using GridSearchCV. The experimental results demonstrate that the optimization process successfully improved the model's generalization capabilities, raising the Accuracy from 0.907 to 0.910 and the F1-Score from 0.893 to 0.897. Most significantly, the AUC score increased from 0.949 to 0.957, indicating a superior ability to distinguish between sentiment classes. However, while the model exhibited high precision in identifying positive and negative polarities, analysis of the confusion matrix revealed limitations in correctly predicting the neutral class, suggesting challenges related to class imbalance. These findings confirm that an optimized CatBoost model is a robust tool for sentiment classification, though future work is recommended to address minority class detection.
Optimizing Javanese script recognition using fine-tuned ResNet-18 and transfer learning Fateah, Nur; Subhan, Subhan; Ifriza, Yahya Nur
IAES International Journal of Artificial Intelligence (IJ-AI) Vol 15, No 1: February 2026
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijai.v15.i1.pp443-453

Abstract

Javanese script, known as Aksara Jawa, is an ancient script used in historical and cultural texts. However, its complex character structure poses challenges for accurate recognition in modern digital applications. This study proposes an optimized classification approach for Aksara Jawa using a fine-tuned ResNet-18 model combined with the Adam optimization algorithm and transfer learning on the Hanacaraka image dataset. By leveraging the residual learning framework of ResNet-18, the model effectively captures deep spatial features of the script while reducing vanishing gradient issues. Fine-tuning is applied to enhance model adaptability, ensuring robust feature extraction specific to Javanese characters. Experimental results demonstrate that the fine-tuned ResNet-18 outperforms conventional deep learning architectures in recognizing Aksara Jawa characters, achieving 93% precision, 91% recall, 91% F1-score, and 91% accuracy. The study further explores the impact of hyperparameter tuning, data augmentation, and dropout regularization on model performance. The findings highlight the effectiveness of transfer learning in resource-limited scenarios, making it a feasible solution for optical character recognition (OCR) applications in Javanese script digitization. This research contributes to the preservation of cultural heritage through advancements in deep learning-based script recognition.