This Author published in this journals
All Journal Jurnal Algoritma
Arni Muarifah Amri
Universitas Telkom

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

Integrasi Express.js dan LLM dalam Pembuatan Soal Otomatis untuk Latihan Anak Disleksia Stevan Andreas; Arni Muarifah Amri; Muhammad Asthi Seta Ari Yuwana; Michael Angello Qadosy Riyadi; Siti Nafiatul Fauziah
Jurnal Algoritma Vol 23 No 1 (2026): Jurnal Algoritma
Publisher : Institut Teknologi Garut

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33364/algoritma/v.23-1.3372

Abstract

Dyslexia is a neurological disorder that affects a child’s ability to read and write, resulting in low literacy levels despite normal intelligence. This study aims to develop a web-based learning system that integrates a Large Language Model and is capable of generating automated practice questions tailored to the needs of children with dyslexia. The system development in this study utilizes a RESTful API architecture using Express.js, MongoDB, and Ollama. The development model employs the ADDIE framework with an Agile approach, while testing was conducted using black-box testing, white-box testing, usability testing, and performance testing. The test results indicate that the system is capable of generating automated practice questions tailored to individual needs, with functionalities operating effectively and a positive user experience. In terms of performance, the system achieved a 100% success rate with 6 concurrent users. However, this study is still limited to a small-scale pilot with low user load, so further optimization is needed for broader implementation. Overall, the integration of Express.js and a local LLM has proven effective in providing a fast, secure, and adaptive learning solution for children with dyslexia.