Article Per Year (5 Year)
p-Index From 2020 - 2025
0.23
P-Index
This Author published in this journals
All Journal Dinasti International Journal of Education Management and Social Science
Unggul Priantoro, Akhmad
Unknown Affiliation
Education

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

Found 1 Documents
Search

 1 
lIntegration of NLP and NLU in the Implementation of Chatbot in Asset Management System Cahya Ash Shoddiqy, Thoha; Unggul Priantoro, Akhmad; Pria Utama, Gunawan
Dinasti International Journal of Education Management And Social Science Vol. 6 No. 2 (2025): Dinasti International Journal of Education Management And Social Science (Decem
Publisher : Dinasti Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.38035/dijemss.v6i2.3716

Abstract

PT XYZ, a startup in the Information Technology sector, developed an asset management application to digitalize the asset management process for its clients. However, as new features were added, the application became more complex, causing difficulties for new users. PT XYZ responded by introducing a customer service system to assist new users in exploring the company’s services and application features. To improve service efficiency while maintaining quality, the company opted to implement a chatbot. The chatbot was designed to provide automatic and responsive assistance, reducing the load on the customer service team and increasing user satisfaction. The author integrated NLP and NLU in designing the chatbot for PT XYZ using the open-source RASA framework. This framework was chosen for its strong capabilities in natural language processing and understanding conversational context. The NLP and NLU models are used to create a customer service engine in the form of text messages that answer questions specifically related to the use of the asset management application. By leveraging this technology, the chatbot can provide relevant and accurate responses, even when faced with variations in language and complex questions. Based on black box testing, the chatbot successfully recognized the intent behind user queries. The testing was conducted to evaluate how well the chatbot understood and responded to user questions. The results, using a confusion matrix, showed that precision, recall, accuracy, and f1-score all achieved a perfect score of 1.0.
Co-Authors Cahya Ash Shoddiqy, Thoha Gunawan Pria Utama