Claim Missing Document
Check
Articles

Utilizing Digital Technology in Church Youth Counseling: The "Teman Baomong" Platform Reaches the Unreached in the GMIT Classis in East Kupang City Widiastuti, Tiwuk; Fanggidae, Adriana; Polly, Yuliyanto T.; Sihotang, D.M; Rumlaklak, N.D; Abdi Keraf, Marselino K.P.
JURNAL TEPAT : Teknologi Terapan untuk Pengabdian Masyarakat Vol 8 No 2 (2025): Collaboration for Accelerated Community Achievement
Publisher : Faculty of Engineering UNHAS

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25042/jurnal_tepat.v8i2.623

Abstract

Adolescent mental health in East Nusa Tenggara Province has become an urgent concern due to increasing cases of emotional mental disorders and limited access to psychological services. To address this issue, the community service team partnered with the Klasis GMIT East Kupang City to develop the Teman Baomong Digital Platform as a web-based mental health consultation service for approximately 12,000 youth under the Klasis. This program aims to improve mental health literacy and access to psychological support that is safe, affordable, and stigma-free through online consultations with psychologists, religious leaders, and peer counselors, as well as the provision of educational content. The implementation methods included: (1) development of the Teman Baomong platform, (2) training of 35 peer counselors, (3) mental health education for 121 adolescents, and (4) provision of individual online consultation services. Evaluation was conducted through pre- and post-tests and a User Acceptance Test (UAT) to assess user acceptance of the platform. The results showed a significant increase in adolescent mental health literacy by 39.8% and enhanced involvement of peer counselors in community assistance. The UAT results from 50 respondents indicated an average score of 94%, demonstrating that the platform is perceived as highly effective and feasible for use. The highest-rated aspect was ease of use (98%), while the lowest was access speed (83.6%) due to internet network limitations in several congregation areas. In conclusion, the implementation of the Teman Baomong platform has effectively improved access to mental health services and literacy among adolescents, and it has strong potential for sustainable development within church and community support ecosystems in East Nusa Tenggara.
Evaluating Sustainable Educational Technology Adoption Models to Bridge Institutional Innovation and Community Driven Learning Practices Tiwuk Widiastuti; Dewantoro Lase; Firman Pratama
International Journal of Educational Technology and Society Vol. 2 No. 3 (2025): September: International Journal of Educational Technology and Society
Publisher : Asosiasi Periset Bahasa Sastra Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.61132/ijets.v2i3.464

Abstract

This study explores the integration of community driven learning practices in the adoption of educational technology and its impact on sustainability. With the rapid advancement of digital tools and platforms, higher education institutions have increasingly adopted online and hybrid learning models to enhance teaching and learning. However, despite the potential benefits, aligning institutional goals with community needs remains a significant challenge. This research utilizes a mixed methods approach, combining stakeholder surveys, policy analysis, and comparative case studies to evaluate the effectiveness of both top down and community aligned adoption models. The findings reveal that community driven models, which involve local stakeholders in the decision making process, lead to higher engagement, better adoption rates, and greater long term sustainability compared to top down approaches. Stakeholders, including educators, students, and administrators, reported that participatory decision making fostered a sense of ownership and ensured the relevance of adopted technologies. The study also identifies key sustainability factors, including participatory decision making, long term community engagement, and contextual relevance, which are crucial for ensuring that educational technologies remain effective and beneficial over time. However, challenges such as resistance to change, lack of resources, and unequal access to technology were found to hinder the successful implementation of sustainable models. The research concludes with practical recommendations for educational institutions and policymakers to adopt community aligned models and ensure equitable access to technology. Future research directions are suggested to further explore the balance between institutional innovation and community driven learning, with a focus on long term outcomes and the adaptability of these models across different educational contexts.
Interpretable Feature Interaction Mining in High-Dimensional Clinical Data Using Hybrid Tree–Neural Models Widiastuti, Tiwuk; Richard , Berlien; Maryo Indra, Manjaruni
Global Science: Journal of Information Technology and Computer Science Vol. 2 No. 1 (2026): March: Global Science: Journal of Information Technology and Computer Science
Publisher : International Forum of Researchers and Lecturers

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70062/globalscience.v2i1.182

Abstract

High-dimensional clinical data exhibit complex and non-linear relationships among patient attributes, where outcomes are often influenced by feature interactions rather than isolated variables. However, many existing machine learning models prioritize predictive performance while providing limited interpretability and insufficient insight into interaction structures. This study aims to address this limitation by developing an interpretable and robust framework for feature interaction mining in clinical data. We propose a hybrid tree–neural modeling framework that explicitly captures and ranks feature interactions while maintaining stable predictive performance. Tree-based ensemble models are employed to identify non-linear interaction patterns, while neural representations enhance learning flexibility and generalization. The framework integrates interaction importance analysis, cross-validation–based stability assessment, and evaluation across multiple data splits to ensure robustness and interpretability. Experiments conducted on a real-world high-dimensional clinical dataset demonstrate that the proposed approach achieves consistent predictive performance, with AUC values ranging from 0.628 to 0.641 across five cross-validation folds (mean AUC ≈ 0.633). Performance remains stable under varying train–test splits, indicating strong generalizability. Interaction analysis reveals that a small number of dominant feature interactions—such as age combined with length of hospital stay and medication count combined with diagnostic information—consistently contribute to model predictions, appearing in over 80% of validation folds. Ablation studies further confirm that removing interaction-aware components leads to noticeable performance degradation, highlighting their importance. In conclusion, this study demonstrates that explicit feature interaction modeling enhances interpretability, stability, and generalization in clinical prediction tasks. The proposed hybrid framework provides a reliable foundation for developing trustworthy and transparent clinical decision-support systems
Co-Authors Abdi Keraf, Marselino K.P. Adi Sebastianus Molla Adriana Fanggidae Agus Setyobudi Ahmad Taufik Ardean Raflian Arfan Y Mauko Baun, Diandra Bertha S. Djahi Bertha Selviana Djahi Bertha Selviana Djahi Bertha Veronika Da Silva Pinto Bloemhard, Putri E Derwin R Sina Derwin R Sina Derwin Rony Sina, Derwin Dewantoro Lase Djahi, Bertha S. Djahi, Bertha Selviana Dumanauw, Yesaya Evanmarch Dwi C Djahilape Emerensye S. Y. Pandie Emerensye Sofia Yublina Pandie Emerensye Sofia Yublina Pandie Fanggidae, Adriana febby, jurgan Fios, Ignasius Kristoforus Siuk Firman Pratama Hanna Florenci Tapikap Immanuel K P Rini Inggrid Raga Djara Juan Rizky Mannuel Ledoh Kabosu, Maria Inansintia Elvira Kornelis Letelay Lehot, Fransisco Ronaldo Lestari, Ayu Triyuni Lete, Patrisius Remby Lobo, Franklin Anugrah Steveinson Mage, Marnon Yolinda Chrisma Malelak, Ruvina Febrianti Maria Louise Ludgardis Muku Marnon C. Y Mage Marylin S. Junias Maryo Indra, Manjaruni Meiton Boru Meiton Boru Meiton Boru Metkono, Denni Irvanto Missa, Wanto I Mola, Sebastian Adi Santoso Mola, Sebastianus Adi Santosa Mustakim Sahdan Naatonis, Djohan Rudolf Andriano Nabuasa, Yelly Yosiana Nelci D Rumlaklak Nelci Dessy Rumlaklak Nelcy Rumlaklak Ngefak, Videl Richard Nita Novita Non, Erwin T. W. Nunes, Ingratcia Pa, Bernard Jose Adrian Junio Ajilo Polly, Yulianto Triwahyuadi Ratu, Nalfayo Christian Richard , Berlien Romy O. D. Djami Rumlaklak, N.D Rumlaklak, Nelci D. Rumlaklak, Nelci Dessy Safitri, Aisyah Rizki Sani, Michelle Sarinah Basri K Sebastianus A S Mola Sebastianus Adi Santoso Mola Sihotang, D.M Sihotang, Dony Martinus Sina, Derwin R. Sintha Lisa Purimahua Suhada, Dimas Tabelak, Dion Stekiko Melfin Tarus, Karen N.V Tas'au, Emilia Thimothy Ariel Masangin Tokan, Diana Inda Carmilla Triyanto Umanailo, Ali Umasangadji, Fachry Muhammad yelly y nabuasa Yoshua Patriot Thundericco Yulianto Triwahyuadi Polly