JudithJeyafreeda@LT-EDI-2023: Using GPT model for recognition of Homophobia/Transphobia detection from social media

Judith Jeyafreeda Andrew


Abstract
Homophobia and Transphobia is defined as hatred or discomfort towards Gay, Lesbian, Transgender or Bisexual people. With the increase in social media, communication has become free and easy. This also means that people can also express hatred and discomfort towards others. Studies have shown that these can cause mental health issues. Thus detection and masking/removal of these comments from the social media platforms can help with understanding and improving the mental health of LGBTQ+ people. In this paper, GPT2 is used to detect homophobic and/or transphobic comments in social media comments. The comments used in this paper are from five (English, Spanish, Tamil, Malayalam and Hindi) languages. The results show that detecting comments in English language is easier when compared to the other languages.
Anthology ID:
2023.ltedi-1.11
Volume:
Proceedings of the Third Workshop on Language Technology for Equality, Diversity and Inclusion
Month:
September
Year:
2023
Address:
Varna, Bulgaria
Editors:
Bharathi R. Chakravarthi, B. Bharathi, Joephine Griffith, Kalika Bali, Paul Buitelaar
Venues:
LTEDI | WS
SIG:
Publisher:
INCOMA Ltd., Shoumen, Bulgaria
Note:
Pages:
78–82
Language:
URL:
https://aclanthology.org/2023.ltedi-1.11
DOI:
Bibkey:
Cite (ACL):
Judith Jeyafreeda Andrew. 2023. JudithJeyafreeda@LT-EDI-2023: Using GPT model for recognition of Homophobia/Transphobia detection from social media. In Proceedings of the Third Workshop on Language Technology for Equality, Diversity and Inclusion, pages 78–82, Varna, Bulgaria. INCOMA Ltd., Shoumen, Bulgaria.
Cite (Informal):
JudithJeyafreeda@LT-EDI-2023: Using GPT model for recognition of Homophobia/Transphobia detection from social media (Andrew, LTEDI-WS 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.ltedi-1.11.pdf