ARC-NLP at ClimateActivism 2024: Stance and Hate Speech Detection by Generative and Encoder Models Optimized with Tweet-Specific Elements

2024-01-01
Kaya, Ahmet Kagan
Ozcelik, Oguzhan
Toraman, Çağrı
Social media users often express hate speech towards specific targets and may either support or refuse activist movements. The automated detection of hate speech, which involves identifying both targets and stances, plays a critical role in event identification to mitigate its negative effects. In this paper, we present our methods for three subtasks of the Climate Activism Stance and Hate Event Detection Shared Task at CASE 2024. For each subtask (i) hate speech identification (ii) targets of hate speech identification (iii) stance detection, we experiment with optimized Transformer-based architectures that focus on tweet-specific features such as hashtags, URLs, and emojis. Furthermore, we investigate generative large language models, such as Llama2, using specific prompts for the first two subtasks. Our experiments demonstrate better performance of our models compared to baseline models in each subtask. Our solutions also achieve third, fourth, and first places respectively in the subtasks.
7th Workshop on Challenges and Applications of Automated Extraction of Socio-Political Events from Text, CASE 2024
Citation Formats
A. K. Kaya, O. Ozcelik, and Ç. Toraman, “ARC-NLP at ClimateActivism 2024: Stance and Hate Speech Detection by Generative and Encoder Models Optimized with Tweet-Specific Elements,” presented at the 7th Workshop on Challenges and Applications of Automated Extraction of Socio-Political Events from Text, CASE 2024, St. Julian’s, Malta, 2024, Accessed: 00, 2024. [Online]. Available: https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85190246489&origin=inward.