Improving Government Helpdesk Service With an AI-Powered Chatbot Built on the Rasa Framework

Helpdesk services are an important component in supporting Information Technology (IT) services. The helpdesk operates as the initial interface for managing and resolving concerns. Helpdesk helps user to get solutions when facing problems while using an IT service. This research focuses on the impac...

Full description

Saved in:
Bibliographic Details
Main Authors: Wirat Moko Hadi Sasmita, Surya Sumpeno, Reza Fuad Rachmadi
Format: Article
Language:English
Published: Ikatan Ahli Informatika Indonesia 2025-04-01
Series:Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi)
Subjects:
Online Access:https://jurnal.iaii.or.id/index.php/RESTI/article/view/6293
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850139580346400768
author Wirat Moko Hadi Sasmita
Surya Sumpeno
Reza Fuad Rachmadi
author_facet Wirat Moko Hadi Sasmita
Surya Sumpeno
Reza Fuad Rachmadi
author_sort Wirat Moko Hadi Sasmita
collection DOAJ
description Helpdesk services are an important component in supporting Information Technology (IT) services. The helpdesk operates as the initial interface for managing and resolving concerns. Helpdesk helps user to get solutions when facing problems while using an IT service. This research focuses on the impact of artificial intelligence (AI)-powered chatbots on the performance of the initial response of government helpdesk services. The chatbot is designed to improve service performance by quickly identifying and classifying reported issues and automatically responding to messages, enabling faster responses. The research proposed a new System Design of a helpdesk system with an AI-based chatbot. The data used comes from Telegram group chat logs, exported in JSON format. We find that the Rasa NLU model with DIET Classifier successfully achieved an accuracy rate of 0.825 in classifying intents, with the precision value of 0.838, recall of 0.829, and F1 score of 0.821 using a Rasa model with cross-validation, where folds is 5 in evaluation. And initial response time was highly improved after using chatbot artificial intelligence from more than 3 hours on the telegram group helpdesk based to an average of 2.15 seconds. These research results suggest AI-Chatbot-based ability to assist the helpdesk team in handling user queries and reports, and improving initial time response.
format Article
id doaj-art-b2c95f1f547947dbb0fadce751936a2e
institution OA Journals
issn 2580-0760
language English
publishDate 2025-04-01
publisher Ikatan Ahli Informatika Indonesia
record_format Article
series Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi)
spelling doaj-art-b2c95f1f547947dbb0fadce751936a2e2025-08-20T02:30:13ZengIkatan Ahli Informatika IndonesiaJurnal RESTI (Rekayasa Sistem dan Teknologi Informasi)2580-07602025-04-019239340310.29207/resti.v9i2.62936293Improving Government Helpdesk Service With an AI-Powered Chatbot Built on the Rasa FrameworkWirat Moko Hadi Sasmita0Surya Sumpeno1Reza Fuad Rachmadi2Institut Teknologi Sepuluh NopemberInstitut Teknologi Sepuluh NopemberInstitut Teknologi Sepuluh NopemberHelpdesk services are an important component in supporting Information Technology (IT) services. The helpdesk operates as the initial interface for managing and resolving concerns. Helpdesk helps user to get solutions when facing problems while using an IT service. This research focuses on the impact of artificial intelligence (AI)-powered chatbots on the performance of the initial response of government helpdesk services. The chatbot is designed to improve service performance by quickly identifying and classifying reported issues and automatically responding to messages, enabling faster responses. The research proposed a new System Design of a helpdesk system with an AI-based chatbot. The data used comes from Telegram group chat logs, exported in JSON format. We find that the Rasa NLU model with DIET Classifier successfully achieved an accuracy rate of 0.825 in classifying intents, with the precision value of 0.838, recall of 0.829, and F1 score of 0.821 using a Rasa model with cross-validation, where folds is 5 in evaluation. And initial response time was highly improved after using chatbot artificial intelligence from more than 3 hours on the telegram group helpdesk based to an average of 2.15 seconds. These research results suggest AI-Chatbot-based ability to assist the helpdesk team in handling user queries and reports, and improving initial time response.https://jurnal.iaii.or.id/index.php/RESTI/article/view/6293chatbotrasahelpdesknatural language understanding
spellingShingle Wirat Moko Hadi Sasmita
Surya Sumpeno
Reza Fuad Rachmadi
Improving Government Helpdesk Service With an AI-Powered Chatbot Built on the Rasa Framework
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi)
chatbot
rasa
helpdesk
natural language understanding
title Improving Government Helpdesk Service With an AI-Powered Chatbot Built on the Rasa Framework
title_full Improving Government Helpdesk Service With an AI-Powered Chatbot Built on the Rasa Framework
title_fullStr Improving Government Helpdesk Service With an AI-Powered Chatbot Built on the Rasa Framework
title_full_unstemmed Improving Government Helpdesk Service With an AI-Powered Chatbot Built on the Rasa Framework
title_short Improving Government Helpdesk Service With an AI-Powered Chatbot Built on the Rasa Framework
title_sort improving government helpdesk service with an ai powered chatbot built on the rasa framework
topic chatbot
rasa
helpdesk
natural language understanding
url https://jurnal.iaii.or.id/index.php/RESTI/article/view/6293
work_keys_str_mv AT wiratmokohadisasmita improvinggovernmenthelpdeskservicewithanaipoweredchatbotbuiltontherasaframework
AT suryasumpeno improvinggovernmenthelpdeskservicewithanaipoweredchatbotbuiltontherasaframework
AT rezafuadrachmadi improvinggovernmenthelpdeskservicewithanaipoweredchatbotbuiltontherasaframework