Article Per Year (5 Year)
p-Index From 2021 - 2026
1.683
P-Index
This Author published in this journals
All Journal Jurnal Ilmiah Ecosystem INTEK: Jurnal Penelitian Journal of Information Systems and Informatics Jurnal Teknologi Elekterika EJOIN : Jurnal Pengabdian Masyarakat Journal of Informatics and Computer Engineering Research
Utomo, Muhammad Nur Yasir
Unknown Affiliation
Agriculture, Biological Sciences & Forestry Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering Economics, Econometrics & Finance Education Electrical & Electronics Engineering Engineering Law, Crime, Criminology & Criminal Justice Public Health Social Sciences

Published : 11 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 11 Documents
Search

 1   2 
WEB-BASED PUBLIC RELATIONS CHATBOT USING LARGE LANGUAGE MODELS AND THE RETRIEVAL-AUGMENTED GENERATION Nuzul1, Andi Muhammad; Utomo, Muhammad Nur Yasir; Indrabulan, Tantri
Journal of Informatics and Computer Engineering Research Vol. 2 No. 2 (2025)
Publisher : Politeknik Negeri Ujung Pandang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31963/jicer.v2i2.6014

Abstract

The Public Relations and Protocol Working Group (Pokja Humas) of Politeknik Negeri Ujung Pandang (PNUP) faces challenges in providing interactive and responsive information services. The official website functions only as a one-way medium, and the high volume of repeated questions causes delays in response time. This study developed a public relations chatbot based on Large Language Model (LLM) using the Retrieval-Augmented Generation (RAG) method to improve information services. The chatbot data were obtained through web scraping of the PNUP official website and internal PDF documents, which were processed through preprocessing, text splitting, and embedding using Hugging Face and stored in a FAISS vectorstore. The system was built using FastAPI as the backend and web-based interfaces for admin and user interactions. The results show that User Acceptance Test (UAT) involving 35 respondents achieved 91.93% acceptance (very good). The Retrieval-Augmented Generation Assessment (RAGAS) evaluation achieved average scores of 0.89 for Faithfulness, 0.91 for Answer Relevancy, 0.89 for Context Precision, and 0.89 for Context Recall, indicating that the chatbot produced relevant and contextually accurate answers.
Co-Authors Abdul Rahman Al Imran, Andi Yusdar BASTIAN, ALVIAN Fansab, Nur Ayu Farahgta Indrabulan, Tantri Khartika, Widya Mochammad Imron Awalludin Muh. Fajri Raharjo Nuzul1, Andi Muhammad Ramadhani, Ainun Zulkiah Rini Nur, Rini Syam, Muh. Fadhil TUNGADI, EDDY Violita, Fajrin Winursito, Anggun Yusri, Iin Karmila