Proceedings of the International Symposium on Religious Literature and Heritage (ISLAGE 2021)

Classification Content in Indonesian Website Da’wah using Text Mining for Detecting Islamic Radical Understanding

Authors
Nahed Nuwairah1, *, Munsyi Munsyi2
1Faculty of Da’wah and Communication Sciences, Islamic State University Antasari Banjarmasin, Indonesia
2Faculty of Da’wah and Communication Sciences, Islamic State University Antasari Banjarmasin, Indonesia
*Corresponding author. Email: nuwairah1975@yahoo.com
Corresponding Author
Nahed Nuwairah
Available Online 17 February 2022.
DOI
10.2991/assehr.k.220206.002How to use a DOI?
Keywords
Islamic Radical Content; SARA; Text Mining; k-NN Algorithm
Abstract

The Islamic radical content in procedural meaning is content that has provoked the violence, spread the hatred and against nationalism through Islamic da’wah in Indonesian website. The radical definition for each country is different, especially in Indonesia. Radical content is identical with provocation issues and ethnic and religious hatred called SARA (Suku, Agama, Ras, Antargolongan). SARA content is challenging to detect due to the large number, unstructured system, and much noise that can be caused by multiple interpretations. This problem can threaten the unity and harmony of the religion. According to this condition, a system is required to distinguish the radical content or not. We propose a text mining approach using the DF threshold and the Human Brain as the feature extraction in this system. The system is divided into several steps are collecting data which is including at pre-processing, text mining, selection features, classification for grouping the data with the class label, similarity calculation for processing data training, and visualization to the radical Islamic content or not radical content. This research is expected to be literate for users who access websites exposed to radical understanding to suppress the spread of provocation on websites in Indonesia. The experimental result shows that using a combination from 10 cross-validation and k-Nearest Neighbor (kNN) as the classification methods achieve 66.37% accuracy performance with 7 k value of kNN method by collected data using web scrapping in the website blocked by the Ministry of Information and Communication Indonesia (Menkominfo).

Copyright
© 2022 The Authors. Published by Atlantis Press SARL.
Open Access
This is an open access article under the CC BY-NC license.

Download article (PDF)

Volume Title
Proceedings of the International Symposium on Religious Literature and Heritage (ISLAGE 2021)
Series
Advances in Social Science, Education and Humanities Research
Publication Date
17 February 2022
ISBN
978-94-6239-538-1
ISSN
2352-5398
DOI
10.2991/assehr.k.220206.002How to use a DOI?
Copyright
© 2022 The Authors. Published by Atlantis Press SARL.
Open Access
This is an open access article under the CC BY-NC license.

Cite this article

TY  - CONF
AU  - Nahed Nuwairah
AU  - Munsyi Munsyi
PY  - 2022
DA  - 2022/02/17
TI  - Classification Content in Indonesian Website Da’wah using Text Mining for Detecting Islamic Radical Understanding
BT  - Proceedings of the International Symposium on Religious Literature and Heritage (ISLAGE 2021)
PB  - Atlantis Press
SP  - 11
EP  - 16
SN  - 2352-5398
UR  - https://doi.org/10.2991/assehr.k.220206.002
DO  - 10.2991/assehr.k.220206.002
ID  - Nuwairah2022
ER  -