Claim Missing Document
Check
Articles

Digital Marketing and Consumer Engagement for Traditional Handwoven Products through a Web-Based Retail System Muhammad Zamroni Uska; Rasyid Hardi Wirasasmita; Rona Firdaus; Yosi Nur Kholisho; Jamaluddin Jamaluddin
JOURNAL OF INFORMATICS AND TELECOMMUNICATION ENGINEERING Vol. 9 No. 2 (2026): Issues January 2026
Publisher : Universitas Medan Area

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31289/jite.v9i2.16500

Abstract

Traditional handwoven products often struggle to reach wider markets due to the continued reliance on conventional selling practices, which limits visibility and reduces opportunities for consumer engagement in digital retail environments. This study aims to develop and evaluate a web-based retail platform that supports the digital marketing of traditional handwoven products and enhances consumer interaction. A Research and Development approach was employed, integrating essential retail features such as product catalog management, ordering processes, user administration, and interaction interfaces. The platform was evaluated through expert validation to assess content relevance, functional testing using automated tools to ensure system accuracy, performance assessment to examine system efficiency, and usability testing involving 25 users to measure ease of use and consumer acceptance. The results demonstrate that the platform performs reliably, achieves complete functional accuracy, and exhibits high usability, indicating strong approval among users. Performance testing also shows that the platform operates efficiently and is suitable for real retail use. The implications of this study suggest that web-based retail platforms can strengthen digital marketing practices, expand market accessibility for traditional artisans, and contribute to improved consumer experience within craft-based retail sectors.
Public Sentiment on Indonesia’s MBG Budget Allocation: Twitter/X Analysis Using IndoBERT Model Muhammad Zamroni Uska; Rasyid Hardi Wirasasmita; Wilda Susanti; Yosi Nur Kholisho
JOURNAL OF INFORMATICS AND TELECOMMUNICATION ENGINEERING Vol. 10 No. 1 (2026): Issues July 2026
Publisher : Universitas Medan Area

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31289/jite.v10i1.17882

Abstract

The increasing use of social media has created opportunities to examine public opinion regarding government policies through sentiment analysis approaches. This study analyzes public sentiment toward the budget allocation of the Makan Bergizi Gratis (MBG) program in Indonesia using Twitter/X data and the IndoBERT model. Data were collected through keyword-based crawling techniques, resulting in 24,836 tweets, which were reduced to 18,742 tweets after preprocessing. The dataset was manually annotated into positive, negative, and neutral sentiment categories before being classified using IndoBERT. The evaluation results indicate that the proposed model achieved strong performance, with an accuracy of 92.41%, precision of 91.86%, recall of 92.03%, F1-score of 91.94%, and ROC-AUC value of 0.961. The findings reveal that negative sentiment dominated public discourse, primarily associated with concerns regarding fiscal sustainability, transparency, and policy priorities. Positive sentiment mainly emphasized nutritional benefits and educational welfare impacts. The study demonstrates that transformer-based NLP models are effective for analyzing Indonesian social media discourse and provides practical insights for evidence-based policymaking and digital governance evaluation.
Gerakan Masyarakat Desa Suralaga Bebas Stunting melalui Optimalisasi Web-Based Literacy 'Stunt Guard' Yosi Nur Kholisho; Jamaluddin Jamaluddin; Kholida Ismatulloh; Rasyid Hardi Wirasasmita; Zamroni Uska; Baiq Desi Dwi Arianti; Mefthafayra Odilia Irham
Al-Tafani: Jurnal Inovasi dan Pengabdian Kepada Masyarakat Vol. 4 No. 1 (2026): Maret
Publisher : Lembaga Einstein College

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.63987/al-tafani.v4i1.246

Abstract

Stunting remains a major public health challenge in Indonesia, particularly in rural areas. This community service program aims to enhance health literacy and digital skills among residents of Suralaga Village by optimizing the “Stunt Guard” web application as an educational and monitoring tool for stunting prevention. Activities included socialization, training, and intensive mentoring for posyandu cadres and mothers of young children. Evaluation using pre-test and post-test revealed a significant increase in participants’ knowledge and preventive behaviors after the intervention. These results indicate that utilizing web-based applications is effective in strengthening community involvement in monitoring child growth and supporting participatory, sustainable stunting prevention efforts. This program is expected to serve as a replicable digital empowerment model to accelerate the reduction of stunting rates in Indonesia.
Interpreting Text-Enriched Dual-Head Multitask Learning for Indonesian Hateful Meme Detection Using Explainable AI Selamet Riadi; Emi Suryadi; Muhamad Masjun Efendi; Bahtiar Imran; Muhammad Zamroni Uska
Jurnal Kecerdasan Buatan dan Teknologi Informasi Vol. 5 No. 3 (2026): September 2026
Publisher : Ninety Media Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.69916/jkbti.v5i3.576

Abstract

Internet memes in Indonesia are frequently weaponized to disseminate implicithate speech through sarcasm and cultural nuances. Automatically detectingsuch content is computationally challenging, and existing deep learningframeworks predominantly operate as opaque black boxes, lacking decisiontransparency. This study implements and optimizes a text-enriched dual-headmultitask learning architecture utilizing IndoBERTweet to concurrently classifyhatefulness and appropriateness within the INDOMEME dataset. Ratherthan processing raw image pixels, we employ a text-enrichment strategy wherevisual semantics are transcribed into textual descriptors via Optical CharacterRecognition and vision-language captioning. To bridge the interpretability gap,we deploy Local Interpretable Model-agnostic Explanations (LIME) to decodethe internal feature attributions of the architecture. Furthermore, advancedtraining optimizations, encompassing cosine annealing, gradient accumulation,class-weighted loss, and dynamic threshold calibration, were engineered toenhance model generalization. Experimental evaluations demonstrate thatthe optimized model achieves a Macro-F1 score of 0.812 for hatefulness and0.820 for appropriateness, surpassing the established baseline. Crucially, theLIME analysis unveils a pivotal finding: despite sharing an identical textualbackbone, the hate-specific head predominantly focuses on lexicons carryingsocial agitation, whereas the appropriateness head prioritizes general normviolations. These empirical findings substantiate that multitask learning enrichessemantic representation quality, offering a transparent framework fortrustworthy content moderation.
Development of an Android-Based Augmented Reality Application Using a Problem-Based Learning Approach to Improve Students’ Digital Literacy Holil Nasari; Rasyid Hardi Wira Sasmita Rasyid Hardi Wira Sasmita; Muhammad Zamroni Uska
Literasi: Jurnal Pendidikan Guru Indonesia Vol. 5 No. 3 (2026): September
Publisher : Lembaga Bale Literasi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58218/literasi.v5i3.5057

Abstract

The rapid evolution of digital technology requires science education to focus not only on conceptual mastery but also on fostering students' digital literacy. The human reproductive system topic, characterized by its abstract nature, is often difficult for students to comprehend when taught solely through conventional lectures and textbooks. This study aims to develop an Augmented Reality (AR) learning media integrated with the Problem-Based Learning (PBL) model via an Android application, named BioReproAR, to cultivate digital literacy among 10th-grade students. Using a Research and Development (R&D) approach guided by the ADDIE framework, the study involved media and methodology experts, content experts, digital literacy experts, biology teachers, and a small-scale trial with 20 10th-grade students. Data were collected using validation sheets, response questionnaires, and documentation. The validation results demonstrated that the developed media is highly valid across media and methodology aspects (89.10%), content accuracy (92.00%), and digital literacy integration (93.75%). Furthermore, feedback from Biology teachers reached 94.00% and student response reached 88.56%, both falling into the "very good" category. BioReproAR is deemed highly feasible for classroom implementation as it effectively visualizes abstract reproductive concepts in concrete 3D formats, presents contextual real-world problems, and encourages students to access and evaluate digital information. Nevertheless, this study is limited to a small-scale trial and did not evaluate cognitive learning outcomes directly. Future research should assess the empirical effectiveness using a quasi-experimental design with a larger sample size and incorporate offline access capabilities
E-Modul Dasar Pemrograman berbasis Android sebagai Media Pembelajaran Bahasa Bahasa C++ Muhammad Zamroni Uska; Rasyid Hardi Wirasasmita; Yosi Nur Kholisho
EDUCATE : Jurnal Teknologi Pendidikan Vol 8 No 02 (2023)
Publisher : Program Studi Teknologi Pendidikan FKIP Universitas Ibn Khaldun, Bogor

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32832/educate.v8i02.8786

Abstract

The basis of programming is to master the basic programming languages, one of which is C++. However, in its application, Hamzanwadi University students are constrained in understanding the C++ language due to the syntax and structure of C++, and the modules used are less specific in content. Our research's objective is to design/develop an android-based C++ programming base e-module while taking into account user feedback on how well users comprehend the fundamental ideas behind the C++ language. ADDIE is the model used to create this E-module, and the type of data used is quantitative. Questionnaires were used to collect the data, which was then quantitatively examined. 22 users and students who attended lectures on basic programming served as the study's subjects.. Our findings suggest that this product has a menu in it: intro page, material menu page, main menu page, video menu, hint menu, and profile menu. The findings of the media experts' assessment came in at 83% (very plausible), and the results of the material experts' assessment came in at 85%. (very feasible). Meanwhile, there was a strong response. Users scored 83% and were labeled as having extremely high proficiency. A high-quality medium or application is deserving of usage and has a very high response rate, allowing users to advance their understanding of C++ programming.
SmartSasak Edu: An Adaptive NLP Mobile Framework for Contextual Sasak Language Learning Muhammad Zamroni Uska; Rasyid Hardi Wirasasmita; Baiq Desi Dwi Arianti; Lalu Habil Mani
Lambda: Jurnal Ilmiah Pendidikan MIPA dan Aplikasinya Vol. 6 No. 3 (2026): Lambda
Publisher : Lembaga Bale Literasi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58218/lambda.v6i3.4721

Abstract

Regional languages face challenges in digital representation, learning accessibility, and the availability of technological resources for educational applications. Existing digital language learning platforms often rely on static vocabulary retrieval with limited contextual understanding and adaptive learning capabilities. This study proposes SmartSasak Edu, an adaptive Natural Language Processing (NLP)-based mobile framework to support contextual Sasak language learning. The study employed a Design Science Research Methodology (DSRM) approach consisting of requirement analysis, framework development, NLP implementation, expert validation, and usability evaluation. The framework integrates Sasak language resources, NLP-based text processing, contextual retrieval mechanisms, adaptive learning features, and mobile interaction. Evaluation was conducted through NLP component testing, expert assessment, and user usability evaluation. The NLP evaluation achieved accuracy scores of 96.40% for text normalization, 95.80% for tokenization, and 91.70% for semantic retrieval, while contextual response generation obtained 89.60% expert agreement. Expert validation resulted in 93.00% linguistic validity and 91.40% technical feasibility. Usability evaluation involving 42 students using the System Usability Scale (SUS) produced a score of 84.25, indicating positive user perceptions of usability. The findings suggest that SmartSasak Edu provides an adaptive approach for supporting regional language learning through NLP-based educational technology and contributes to low-resource NLP and AI-supported language education research.