SISTEM PENDETEKSI LOKASI SEBARAN PENYAKIT COVID-19 BERDASARKAN INFORMASI KORPUS BERBAHASA INDONESIA DI TWITTER DENGAN PENDEKATAN EVENT EXTRACTION

FATHONI, FATHONI and Erwin, Erwin and Abdiansah, Abdiansah (2024) SISTEM PENDETEKSI LOKASI SEBARAN PENYAKIT COVID-19 BERDASARKAN INFORMASI KORPUS BERBAHASA INDONESIA DI TWITTER DENGAN PENDEKATAN EVENT EXTRACTION. Doctoral thesis, Sriwijaya University.

	Text RAMA_21001_03013622126024.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (4MB) | Request a copy
	Text RAMA_21001_03013622126024_0029017101_0001108401_01_front_ref.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (1MB)
	Text RAMA_21001_03013622126024_0029017101_0001108401_02.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (1MB) | Request a copy
	Text RAMA_21001_03013622126024_0029017101_0001108401_03.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (954kB) | Request a copy
	Text RAMA_21001_03013622126024_0029017101_0001108401_04.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (1MB) | Request a copy
	Text RAMA_21001_03013622126024_0029017101_0001108401_05.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (436kB) | Request a copy
	Text RAMA_21001_03013622126024_0029017101_0001108401_06_ref.pdf - Bibliography Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (707kB) | Request a copy
	Text RAMA_21001_03013622126024_0029017101_0001108401_07_lamp.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (607kB) | Request a copy

Abstract

The emergence of the Covid-19 Virus at the end of 2019 in Wuhan, China has created tremendous panic around the world. Referring to the Aljazera.com report in 2020, the speed of the spread of the Covid-19 Virus reached 10 times compared to the spread of SARS and Bird Flu. The speed of transmission of the Covid-19 Virus has caused the virus to have arrived in Indonesia (Jakarta) for less than 4 months, namely in March 2020. Many strategies can be done to respond to the speed of the spread of Covid-19, one of which is by utilizing the development and utilization of information technology. The development of ICT has changed the behavior of the world community and Indonesia in disseminating information on online social media, such as on Twitter. Based on the initial observations that researchers made, a lot of fast information was conveyed by twitter users who conveyed news of the spread of Covid-19 at an incident location in Indonesia. This condition provides new research opportunities to utilize and capture information on the location of the spread of Covid-19 in Indonesia through datasets on Twitter. This study discusses the development of a model that can detect the location of the occurrence of the spread of the covid19 virus in Indonesia with an Event Extraction approach. The model developed will carry out the sentence extraction process using the Regular Expression (Regex) method that has been modified and adapted to research needs and Agorithma One-Dimensional (1D) Convolutional Neural Networks (1D CNN). Regular Expression processes sentence extraction of unstructured corpus data obtained from twitter servers based on event trigger and event argument knowledge taught to the model. To test the performance and accuracy of sentence extraction results carried out by the model, researchers used the Human Intelligence Task and Cross Validation methods. This research succeeded in developing a sentence extraction model that can detect and identify the location of the corona virus spread event in Indonesia in digital (spatial) map format with an accuracy rate of 98.58% and an F1-Score value of 98.92%. The model developed can be used by the government and the community as an early warning that there has been an event of disease outbreak spread in a certain location in Indonesia

Item Type:	Thesis (Doctoral)
Uncontrolled Keywords:	Covid-19, Event Extraction, Regex, 1D CNN, Indonesia
Subjects:	Q Science > QA Mathematics > QA75-76.95 Calculating machines > QA75.5.A142 Computer science. Information society. Information technology.
Divisions:	03-Faculty of Engineering > 21001-Engineering Science (S3)
Depositing User:	Mr. Fathoni Cholil
Date Deposited:	29 Apr 2024 06:17
Last Modified:	29 Apr 2024 06:17
URI:	http://repository.unsri.ac.id/id/eprint/143458

Actions (login required)

View Item