Understanding the Effect of Gender and Stance in Opinion Expression in Debates on “Abortion”

Esin Durmus, Claire Cardie


Abstract
In this paper, we focus on understanding linguistic differences across groups with different self-identified gender and stance in expressing opinions about ABORTION. We provide a new dataset consisting of users’ gender, stance on ABORTION as well as the debates in ABORTION drawn from debate.org. We use the gender and stance information to identify significant linguistic differences across individuals with different gender and stance. We show the importance of considering the stance information along with the gender since we observe significant linguistic differences across individuals with different stance even within the same gender group.
Anthology ID:
W18-1110
Volume:
Proceedings of the Second Workshop on Computational Modeling of People’s Opinions, Personality, and Emotions in Social Media
Month:
June
Year:
2018
Address:
New Orleans, Louisiana, USA
Venues:
NAACL | PEOPLES | WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
69–75
Language:
URL:
https://aclanthology.org/W18-1110
DOI:
10.18653/v1/W18-1110
Bibkey:
Cite (ACL):
Esin Durmus and Claire Cardie. 2018. Understanding the Effect of Gender and Stance in Opinion Expression in Debates on “Abortion”. In Proceedings of the Second Workshop on Computational Modeling of People’s Opinions, Personality, and Emotions in Social Media, pages 69–75, New Orleans, Louisiana, USA. Association for Computational Linguistics.
Cite (Informal):
Understanding the Effect of Gender and Stance in Opinion Expression in Debates on “Abortion” (Durmus & Cardie, 2018)
Copy Citation:
PDF:
https://aclanthology.org/W18-1110.pdf