Claim Missing Document
Check
Articles

Found 3 Documents
Search

SERAYA: A Mobile App for Mental Health with Personalized Self-Healing Recommendations Based on Psychological Assessment Enggi Wira Praja Putri Taufani; Umar Zaky
Jurnal Teknokes Vol. 18 No. 3 (2025): September
Publisher : Jurusan Teknik Elektromedik, Politeknik Kesehatan Kemenkes Surabaya, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Mental health disorders are a crucial public health issue in Indonesia, as reflected in the 2023 National Health Survey (SKI), which reported that 2.0% of the population aged ≥15 years old were diagnosed with mental health problems, and approximately 20% of the 250 million people experiencing mental health problems do not yet have access to adequate services. Although many previous studies have developed digital applications, such as “Serenity” and “CERDAS” in Indonesia for psychological assessment using instruments such as the DASS-21, these applications only provide general recommendations and do not provide personalized self-healing guidance. To address this gap, this study developed and tested “SERAYA”, a mobile application designed not only to assess mental health levels but also to provide self-healing recommendations. This application integrates two standard instruments, the DASS-21 and the PSS-10, to measure depression, anxiety, stress, and perceived stress. A rule-based expert system using forward chaining processes the assessment scores; for example, “IF DASS-21 depression score ≥ 28 THEN recommendation = ‘CBT Therapy’”. Based on this score, the system generates specific recommendations or direct referrals to mental health professionals for severe cases. SERAYA's functionality was verified through successful black-box testing. Initial usability assessments using the System Usability Scale (SUS) with 11 respondents yielded an average score of 80.68, indicating good usability and ease of learning for early users. While these initial results are encouraging, they are derived from a limited, non-clinical sample and cannot be generalized to the entire Indonesian population. Overall, this study demonstrates that “SERAYA” serves as a viable proof-of-concept for providing personalized early mental health support and illustrates the potential of rule-based systems in digital health applications. Future research should focus on larger-scale validation, clinical integration for professional referrals, and the application of machine learning techniques to enable dynamic and tailored personalization.
Pengaruh Penyesuaian Diri Terhadap Motivasi Belajar Pada Mahasiswa Rantau Prasetyoaji, Ari; Umar Zaky; Tati Indriani; Rizka Amanah
G-Couns: Jurnal Bimbingan dan Konseling Vol. 8 No. 3 (2024): Agustus 2024. G-Couns: Jurnal Bimbingan dan Konseling
Publisher : Universitas PGRI Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31316/gcouns.v8i3.5057

Abstract

Proses penyesuaian diri sangat penting, khusunya bagi mahasiswa rantau yang baru mengenal lingkungan baru. Ketidakmampuan dalam menyesuaian diri dengan baik dilingkungan baru berpengaruh pada motivasi belajar. Penelitian ini bertujuan untuk mengetahui pengaruh penyesuaian diri terhadap motivasi belajar pada mahasiswa rantau di Universitas Teknologi Yogyakarta. Metode penelitian ini yaitu metode kuantitatif dengan populasi seluruh mahasiswa rantau di Universitas Teknologi Yogyakarta dengan sampel sebanyak 126 mahasiswa rantau, dengan teknik Stratified Random Sampling. Instrumen yang digunakan yaitu skala penyesuaian diri dan skala motivasi belajar. Analisis data dalam penelitian ini yaitu menggunakan uji regresi linear sederhana. Hasil penelitian menunjukkan perolehan nilai signifikansi sebesar 0,000 < 0,05 dan t hitung > t tabel (13,218 > 1,979). Kesimpulan pada penelitian ini yaitu terdapat pengaruh yang signifikan penyesuaian diri terhadap motivasi belajar pada mahasiswa rantau di Universita Teknologi Yogyakarta. Kata kunci: penyesuaian diri, motivasi belajar, mahasiswa rantau
Cross-Lingual Sentiment Analysis for Indonesian Monetary Policy Akbar Ramadhan; Umar Zaky
Journal of Scientific Research, Education, and Technology (JSRET) Vol. 4 No. 4 (2025): Vol. 4 No. 4 2025
Publisher : Kirana Publisher (KNPub)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58526/jsret.v4i4.943

Abstract

This research develops a cross-lingual sentiment analysis system (RoBERTa-IndoBERT) to monitor public opinion on Bank Indonesia’s 2025 monetary policy from X (Twitter), addressing the scarcity of Indonesian labels and noisy social media text. We introduce a "translate-then-classify" pipeline: Indonesian posts are translated into English, auto-labeled by a mature English RoBERTa model, and these labels are used to fine-tune IndoBERT on the original texts. We compare this cross-lingual (CL) approach, with and without back-translation (BT) augmentation, against a baseline Indo-only model. Performance measured by Accuracy and Macro-F1 indicates the CL pipeline is substantially better than the baseline. The complete model (IndoBERT + CL + BT) yields a Macro-F1 of 98.1%, a 2.8 percentage point (pp) improvement over the baseline (95.3%). Qualitative error analysis corroborates the CL model is more stable, less prone to extreme polarity flips, and better at detecting implicit sentiment. This research demonstrates that a CL auto-labeling pipeline is an efficient and resilient solution for Indonesian sentiment analysis in low-resource scenarios.