Article Per Year (5 Year)
p-Index From 2020 - 2025
0.23
P-Index
This Author published in this journals
All Journal JURNAL MEDIA INFORMATIKA BUDIDARMA
Erbina Selvia Br Perangin-Angin
Telkom University, Bandung
Computer Science & IT Control & Systems Engineering Electrical & Electronics Engineering

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

Found 1 Documents
Search

 1 
Question Answering using Ontology for Sumedang Larang History with Support Vector Machine Based on Telegram Bot Erbina Selvia Br Perangin-Angin; Z. K. A Baizal; Donni Richasdy
JURNAL MEDIA INFORMATIKA BUDIDARMA Vol 6, No 4 (2022): Oktober 2022
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/mib.v6i4.4574

Abstract

Technological developments affect many aspects, one of which is historical education. History lessons can shape students' personalities and encourage an interest in historical knowledge. There are many stories from Indonesian history, one of which is the Sumedang Larang Kingdom. The Sumedang Larang Kingdom is one of the Islamic kingdoms in Pasundan. However, not many people know about this kingdom. The millennial generation is technologically advanced, so they can take advantage of technological advances to quickly introduce the history of Sumedang Larang. One of them utilizes the telegram bot using the Application Programming Interface (API), which can connect the system to the telegram platform. In addition, this technology can be used as a history learning attraction using the question answering system (QA). Our research aims to build a QA system that can introduce the history of Sumedang Larang to the millennial generation. Because this system uses ontology knowledge with concepts related to the Sumedang Larang domain, it can focus on the history of Sumedang Larang. Applying the support vector machine (SVM) algorithm to process classification text can make it easier to search for text categories. The test results show the performance of the SVM method with a test size parameter of 0.5, such as 74% and 78%. The performance test results are accuracy scores in the subject category and object classification.
Co-Authors Donni Richasdy ZK Abdurahman Baizal