TY - GEN
T1 - TeamX@DravidianLangTech-ACL2022
T2 - 2nd Workshop on Speech and Language Technologies for Dravidian Languages, Proceedings of the Workshop, DravidianLangTech 2022
AU - Nandi, Rabindra Nath
AU - Alam, Firoj
AU - Nakov, Preslav
N1 - Publisher Copyright:
© 2022 Association for Computational Linguistics.
PY - 2022
Y1 - 2022
N2 - The spread of fake news, propaganda, misinformation, disinformation, and harmful content online raised concerns among social media platforms, government agencies, policymakers, and society as a whole. This is because such harmful or abusive content leads to several consequences to people such as physical, emotional, relational, and financial. Among different harmful content trolling-based online content is one of them, where the idea is to post a message that is provocative, offensive, or menacing with an intent to mislead the audience. The content can be textual, visual, a combination of both, or a meme. In this study, we provide a comparative analysis of troll-based memes classification using the textual, visual, and multimodal content. We report several interesting findings in terms of code-mixed text, multimodal setting, and combining an additional dataset, which shows improvements over the majority baseline.
AB - The spread of fake news, propaganda, misinformation, disinformation, and harmful content online raised concerns among social media platforms, government agencies, policymakers, and society as a whole. This is because such harmful or abusive content leads to several consequences to people such as physical, emotional, relational, and financial. Among different harmful content trolling-based online content is one of them, where the idea is to post a message that is provocative, offensive, or menacing with an intent to mislead the audience. The content can be textual, visual, a combination of both, or a meme. In this study, we provide a comparative analysis of troll-based memes classification using the textual, visual, and multimodal content. We report several interesting findings in terms of code-mixed text, multimodal setting, and combining an additional dataset, which shows improvements over the majority baseline.
UR - http://www.scopus.com/inward/record.url?scp=85137178350&partnerID=8YFLogxK
U2 - 10.18653/v1/2022.dravidianlangtech-1.13
DO - 10.18653/v1/2022.dravidianlangtech-1.13
M3 - Conference contribution
AN - SCOPUS:85137178350
T3 - DravidianLangTech 2022 - 2nd Workshop on Speech and Language Technologies for Dravidian Languages, Proceedings of the Workshop
SP - 79
EP - 85
BT - DravidianLangTech 2022 - 2nd Workshop on Speech and Language Technologies for Dravidian Languages, Proceedings of the Workshop
A2 - Chakravarthi, Bharathi Raja
A2 - Priyadharshini, Ruba
A2 - Madasamy, Anand Kumar
A2 - Krishnamurthy, Parameswari
A2 - Sherly, Elizabeth
A2 - Mahesan, Sinnathamby
PB - Association for Computational Linguistics (ACL)
Y2 - 26 May 2022
ER -