Melola Discovery

← Melola Discovery

Journal SINTA 1

Sara Detection on Social Media Using Deep Learning Algorithm Development

Journal of Applied Engineering and Technological Science (JAETS) · Vol. 6 No. 1 (2024) · pp. 225–237

DOI
10.37385/jaets.v6i1.5390
ISSN
2715-6079, 2715-6087
Published
2024-12-15
Publisher
Yayasan Riset dan Pengembangan Intelektual (YRPI)
Language
en

Abstract

Social media has become a key platform for disseminating information and opinions, particularly in Indonesia, where SARA (Ethnicity, Religion, Race, and Intergroup) issues can fuel social tensions. To address this, developing an automated system to detect and classify harmful content is essential. This study develops a deep learning model using Convolutional Neural Network (CNN) and Bidirectional Long Short-Term Memory (BiLSTM) to detect SARA-related comments on Twitter. The method involves data collection through web scraping, followed by cleaning, manual labeling, and text preprocessing. To address data imbalance, SMOTE (Synthetic Minority Over-sampling Technique) is applied, while early stopping prevents overfitting. Model performance is evaluated using precision, recall, and F1-score. The results demonstrate that SMOTE significantly improves model performance, particularly in detecting minority-class SARA comments. CNN+SMOTE achieves a accuracy of 93%, and BiLSTM+SMOTE records a recall of 88%, effectively capturing patterns in SARA and non-SARA data. With SMOTE and early stopping, the model successfully manages class imbalance and reduces overfitting. This research supports efforts to curtail hate speech on social media, especially in the Indonesian context, where SARA-related issues often dominate public discourse.

Keywords

Collaboration network of the authors

40 authors · 113 co-authorship links · 26 across different organisations · showing the 40 most connected

Hover or tap a name to highlight its co-authors. Double-click to open the author's page.

  • Mulawarman University
  • STMIK Banjarbaru
  • Musamus Merauke University
  • Universitas Respati Yogyakarta
  • STMIK El Rahma Yogyakarta
  • Hasanuddin University
  • Universitas Islam Negeri Antasari Banjarmasin
  • Affiliation unknown
  • Different organisations
  • Same organisation
  • Affiliation unknown
  • Thicker line = more joint articles · bigger circle = more articles
Show as table
Co-authorOrganisationJoint articles
Refni WahyuniAffiliation unknown11
Anindita SeptiariniMulawarman University5
Anindita SeptiariniAffiliation unknown5
Anita FebrianiAffiliation unknown4
Budi RahmaniSTMIK Banjarbaru3
Heru IsmantoMusamus Merauke University3
Didit SuprihantoMulawarman University3
Novianti PuspitasariMulawarman University3
Muhardi MuhardiAffiliation unknown3
Yesica DevisAffiliation unknown3
Ali Basrah PulunganAffiliation unknown3
Uci RahmalisaAffiliation unknown3
Dyna Marisa KhairinaMulawarman University2
Agus Qomaruddin MunirUniversitas Respati Yogyakarta2
Andri SyafriantoSTMIK El Rahma Yogyakarta2
Ummul HairahMulawarman University2
Tarina DashelaAffiliation unknown2
Bistari BistariAffiliation unknown2
Rustam RustamHasanuddin University2
Veven VevenAffiliation unknown2
Naima BelarbiAffiliation unknown2
Mbunwe Muncho JosephineAffiliation unknown2
Eka SabnaAffiliation unknown2
Mardeni MardeniAffiliation unknown2
Hugo ApriliantoSTMIK Banjarbaru1
Andi TejawatiMulawarman University1
Surya Eka PriyatnaUniversitas Islam Negeri Antasari Banjarmasin1
Yuriadi IlmiAffiliation unknown1
Sadik IkhsanAffiliation unknown1
Novriadi NovriadiAffiliation unknown1
Silvia MeilinaAffiliation unknown1
Melda YenniAffiliation unknown1

Affiliations come from OpenAlex; journal OAI-PMH metadata carries none. Authors without an OpenAlex ID are matched by name, which can merge or split people.

Metadata source: OAI-PMH (metadata jurnal) https://journal.yrpipku.com/index.php/jaets/oai, first harvested 9 Nov 2026, last seen 9 Nov 2026.
Original metadata (oai_dc) 
<oai_dc:dc xmlns="http://www.openarchives.org/OAI/2.0/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:oai_dc="http://www.openarchives.org/OAI/2.0/oai_dc/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/oai_dc/  http://www.openarchives.org/OAI/2.0/oai_dc.xsd">
	<dc:title xml:lang="en">Sara Detection on Social Media Using Deep Learning Algorithm Development  </dc:title>
	<dc:creator xml:lang="en">Anam, M. Khairul</dc:creator>
	<dc:creator xml:lang="en">Van FC, Lucky Lhaura</dc:creator>
	<dc:creator xml:lang="en">Hamdani, Hamdani</dc:creator>
	<dc:creator xml:lang="en">Rahmaddeni, Rahmaddeni</dc:creator>
	<dc:creator xml:lang="en">Junadhi, Junadhi</dc:creator>
	<dc:creator xml:lang="en">Firdaus, Muhammad Bambang</dc:creator>
	<dc:creator xml:lang="en">Syahputra, Irwanda</dc:creator>
	<dc:creator xml:lang="en">Irawan, Yuda</dc:creator>
	<dc:subject xml:lang="en">Deep Learning</dc:subject>
	<dc:subject xml:lang="en">SARA Comments</dc:subject>
	<dc:subject xml:lang="en">SARA Detection</dc:subject>
	<dc:subject xml:lang="en">SMOTE</dc:subject>
	<dc:subject xml:lang="en">Social Media Classification</dc:subject>
	<dc:description xml:lang="en">Social media has become a key platform for disseminating information and opinions, particularly in Indonesia, where SARA (Ethnicity, Religion, Race, and Intergroup) issues can fuel social tensions. To address this, developing an automated system to detect and classify harmful content is essential. This study develops a deep learning model using Convolutional Neural Network (CNN) and Bidirectional Long Short-Term Memory (BiLSTM) to detect SARA-related comments on Twitter. The method involves data collection through web scraping, followed by cleaning, manual labeling, and text preprocessing. To address data imbalance, SMOTE (Synthetic Minority Over-sampling Technique) is applied, while early stopping prevents overfitting. Model performance is evaluated using precision, recall, and F1-score. The results demonstrate that SMOTE significantly improves model performance, particularly in detecting minority-class SARA comments. CNN+SMOTE achieves a accuracy of 93%, and BiLSTM+SMOTE records a recall of 88%, effectively capturing patterns in SARA and non-SARA data. With SMOTE and early stopping, the model successfully manages class imbalance and reduces overfitting. This research supports efforts to curtail hate speech on social media, especially in the Indonesian context, where SARA-related issues often dominate public discourse.</dc:description>
	<dc:publisher xml:lang="en">Yayasan Riset dan Pengembangan Intelektual (YRPI)</dc:publisher>
	<dc:date>2024-12-15</dc:date>
	<dc:type>info:eu-repo/semantics/article</dc:type>
	<dc:type>info:eu-repo/semantics/publishedVersion</dc:type>
	<dc:format>application/pdf</dc:format>
	<dc:identifier>https://journal.yrpipku.com/index.php/jaets/article/view/5390</dc:identifier>
	<dc:identifier>10.37385/jaets.v6i1.5390</dc:identifier>
	<dc:source xml:lang="en">Journal of Applied Engineering and Technological Science (JAETS); Vol. 6 No. 1 (2024): Journal of Applied Engineering and Technological Science (JAETS); 225-237</dc:source>
	<dc:source>2715-6079</dc:source>
	<dc:source>2715-6087</dc:source>
	<dc:source>10.37385/jaets.v6i1</dc:source>
	<dc:language>en</dc:language>
	<dc:relation>https://journal.yrpipku.com/index.php/jaets/article/view/5390/3687</dc:relation>
	<dc:rights xml:lang="en">Copyright (c) 2024 Journal of Applied Engineering and Technological Science (JAETS)</dc:rights>
</oai_dc:dc>