Unmasking implicit abuse: a datacentric approach to detect online abusive language

الموضوعات

إدارة

الملخص

The rise of social media platforms has witnessed a disturbing increase in online abusive behavior, causing psychological harm, especially among children. This study focuses on detecting implicit abusive language, often overlooked in favor of explicit abuse. Implicit abuse conceals derogatory language within seemingly positive expressions, making it harder to identify. Using Twitter data, we collected and annotated a dataset distinguishing implicit, explicit, and non-abusive language. Our research leveraged traditional, deep learning, and transfer learning models to detect online abusive language. The Ensemble BERT model achieved a remarkable F1 score of 0.72 and AUC of 0.81 in detecting Implicit Abuse versus not abusive content. This research provides a deeper understanding of the nuances of online abuse and offers a significant step toward creating a safer online environment that promotes healthy digital interactions and the well- being of users.

روابط وملفات

التعريف والنوع

رقم الوثيقة

098b0cb5-fe98-497f-a524-8efb66643cf9

رقم العقد

0

نوع الوسائط

Crawler

نوع المحتوى

الرسائل العلمية

صيغة المصدر

رسائل ماجيستير

نوع الملف

pdf text

أسماء الملفات

2325855_1.pdf

بيانات النشر

ألقاب المؤلفين

[{"name_ar":"نهى عبدالله أباردازو","title_ar":"اعداد","title_en":"Preparation"},{"name_ar":"وائل خريش","title_ar":"اشراف","title_en":"Supervision"}]

اللغة

English

المصدر والدورية

اسم المصدر

Unmasking implicit abuse: a datacentric approach to detect online abusive language

المحتوى والصفحات

عدد الصفحات

0

كلمات الباحثين

Show simple item record dc.contributor.advisor Khreich, Wael dc.contributor.author Abardazzou, Nouha dc.date.accessioned 2023-12-18T06:18:06Z dc.date.available 2023-12-18T06:18:06Z dc.date.issued 2023-12-18 dc.date.submitted 2023-12-15 dc.identifier.uri http://hdl.handle.net/10938/24255 dc.description.abstract The rise of social media platforms has witnessed a disturbing increase in online abusive behavior, causing psychological harm, especially among children. This study focuses on detecting implicit abusive language, often overlooked in favor of explicit abuse. Implicit abuse conceals derogatory language within seemingly positive expressions, making it harder to identify. Using Twitter data, we collected and annotated a dataset distinguishing implicit, explicit, and non-abusive language. Our research leveraged traditional, deep learning, and transfer learning models to detect online abusive language. The Ensemble BERT model achieved a remarkable F1 score of 0.72 and AUC of 0.81 in detecting Implicit Abuse versus not abusive content. This research provides a deeper understanding of the nuances of online abuse and offers a significant step toward creating a safer online environment that promotes healthy digital interactions and the well- being of users. dc.subject Machine learning

إشراف وإعداد

الإشراف

وائل خريش

الإعداد

نهى عبدالله أباردازو

الاقتباسات الببليوغرافية