Islamophobic Tweet Detection using Transfer Learning

Mohd Belal, Ghufran Ullah, Abdullah Ahmad Khan

Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingsScientificpeer-review


Segregating Islamophobic hate speech from other instances of offensive language is a serious hurdle for automatic hate-speech detection on social media platforms such as Twitter. Because lexical detection methods classify all messages containing particular terms like hate speech, previous work using supervised learning has failed to differentiate between these categories. This task is complex due to the level of difficulty in natural language constructs. We have worked on a transfer learning approach using Universal Language Model Fine-tuning (ULMFIT), an efficient method that can be applied to classification tasks. Our method gave more than 80 percent accuracy and the confusion matrix thus formed was successfully able to classify those datasets proportionally into each block. The use of Deep learning in text classification has been underutilized. This method will contribute to solving the spread of Islamophobia which hasn't been taken into consideration when taking action against online hate.
Original languageEnglish
Title of host publication2022 International Conference on Connected Systems & Intelligence (CSI)
ISBN (Electronic)978-1-6654-5815-3
Publication statusPublished - 31 Aug 2022
MoE publication typeA4 Conference publication
EventInternational Conference on Connected Systems & Intelligence - Trivandrum, India
Duration: 31 Aug 20222 Sept 2022


ConferenceInternational Conference on Connected Systems & Intelligence
Abbreviated titleCSI


Dive into the research topics of 'Islamophobic Tweet Detection using Transfer Learning'. Together they form a unique fingerprint.

Cite this