Instagram-Based Benchmark Dataset for Cyberbullying Detection in Arabic Text

Background: the ability to use social media to communicate without revealing one’s real identity has created an attractive setting for cyberbullying. Several studies targeted social media to collect their datasets with the aim of automatically detecting offensive language. However, the majority of t...

Full description

Saved in:
Bibliographic Details
Main Author: ALBayari, Reem (author)
Other Authors: Abdallah, Sherief (author)
Published: 2022
Subjects:
Online Access:https://bspace.buid.ac.ae/handle/1234/3117
https://doi.org/10.3390/data7070083.
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1862980613535956992
author ALBayari, Reem
author2 Abdallah, Sherief
author2_role author
author_facet ALBayari, Reem
Abdallah, Sherief
author_role author
dc.creator.none.fl_str_mv ALBayari, Reem
Abdallah, Sherief
dc.date.none.fl_str_mv 2022
2025-05-24T12:51:30Z
2025-05-24T12:51:30Z
dc.identifier.none.fl_str_mv ALBayari, R. and Abdallah, S. (2022) “Instagram-Based Benchmark Dataset for Cyberbullying Detection in Arabic Text,” Data, 7(7), p. 83.
https://bspace.buid.ac.ae/handle/1234/3117
https://doi.org/10.3390/data7070083.
dc.language.none.fl_str_mv en
dc.publisher.none.fl_str_mv MDPI
dc.relation.none.fl_str_mv Datav7 n7 (2022): 83
dc.subject.none.fl_str_mv cyberbullying; offensive language; Arabic dialect
dc.title.none.fl_str_mv Instagram-Based Benchmark Dataset for Cyberbullying Detection in Arabic Text
dc.type.none.fl_str_mv Article
description Background: the ability to use social media to communicate without revealing one’s real identity has created an attractive setting for cyberbullying. Several studies targeted social media to collect their datasets with the aim of automatically detecting offensive language. However, the majority of the datasets were in English, not in Arabic. Even the few Arabic datasets that were collected, none focused on Instagram despite being a major social media platform in the Arab world. (2) Methods: we use the official Instagram APIs to collect our dataset. To consider the dataset as a benchmark, we use SPSS (Kappa statistic) to evaluate the inter-annotator agreement (IAA), as well as examine and evaluate the performance of various learning models (LR, SVM, RFC, and MNB). (3) Results: in this research, we present the first Instagram Arabic corpus (sub-class categorization (multi-class)) focusing on cyberbullying. The dataset is primarily designed for the purpose of detecting offensive language in texts. We end up with 200,000 comments, of which 46,898 comments were annotated by three human annotators. The results show that the SVM classifier outperforms the other classifiers, with an F1 score of 69% for bullying comments and 85 percent for positive comments.
id budr_c9b9cbb243108c1a06c3f1b00d0e148f
identifier_str_mv ALBayari, R. and Abdallah, S. (2022) “Instagram-Based Benchmark Dataset for Cyberbullying Detection in Arabic Text,” Data, 7(7), p. 83.
language_invalid_str_mv en
network_acronym_str budr
network_name_str The British University in Dubai repository
oai_identifier_str oai:bspace.buid.ac.ae:1234/3117
publishDate 2022
publisher.none.fl_str_mv MDPI
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
spelling Instagram-Based Benchmark Dataset for Cyberbullying Detection in Arabic TextALBayari, ReemAbdallah, Sheriefcyberbullying; offensive language; Arabic dialectBackground: the ability to use social media to communicate without revealing one’s real identity has created an attractive setting for cyberbullying. Several studies targeted social media to collect their datasets with the aim of automatically detecting offensive language. However, the majority of the datasets were in English, not in Arabic. Even the few Arabic datasets that were collected, none focused on Instagram despite being a major social media platform in the Arab world. (2) Methods: we use the official Instagram APIs to collect our dataset. To consider the dataset as a benchmark, we use SPSS (Kappa statistic) to evaluate the inter-annotator agreement (IAA), as well as examine and evaluate the performance of various learning models (LR, SVM, RFC, and MNB). (3) Results: in this research, we present the first Instagram Arabic corpus (sub-class categorization (multi-class)) focusing on cyberbullying. The dataset is primarily designed for the purpose of detecting offensive language in texts. We end up with 200,000 comments, of which 46,898 comments were annotated by three human annotators. The results show that the SVM classifier outperforms the other classifiers, with an F1 score of 69% for bullying comments and 85 percent for positive comments.MDPI2025-05-24T12:51:30Z2025-05-24T12:51:30Z2022ArticleALBayari, R. and Abdallah, S. (2022) “Instagram-Based Benchmark Dataset for Cyberbullying Detection in Arabic Text,” Data, 7(7), p. 83.https://bspace.buid.ac.ae/handle/1234/3117https://doi.org/10.3390/data7070083.enDatav7 n7 (2022): 83oai:bspace.buid.ac.ae:1234/31172025-05-24T12:53:08Z
spellingShingle Instagram-Based Benchmark Dataset for Cyberbullying Detection in Arabic Text
ALBayari, Reem
cyberbullying; offensive language; Arabic dialect
title Instagram-Based Benchmark Dataset for Cyberbullying Detection in Arabic Text
title_full Instagram-Based Benchmark Dataset for Cyberbullying Detection in Arabic Text
title_fullStr Instagram-Based Benchmark Dataset for Cyberbullying Detection in Arabic Text
title_full_unstemmed Instagram-Based Benchmark Dataset for Cyberbullying Detection in Arabic Text
title_short Instagram-Based Benchmark Dataset for Cyberbullying Detection in Arabic Text
title_sort Instagram-Based Benchmark Dataset for Cyberbullying Detection in Arabic Text
topic cyberbullying; offensive language; Arabic dialect
url https://bspace.buid.ac.ae/handle/1234/3117
https://doi.org/10.3390/data7070083.