MultiClimate: Multimodal Stance Detection on Climate Change Videos
Wang, Jiawen, Zuo, Longfei, Peng, Siyao, Plank, Barbara
–arXiv.org Artificial Intelligence
Climate change (CC) has attracted increasing attention in NLP in recent years. However, detecting the stance on CC in multimodal data is understudied and remains challenging due to a lack of reliable datasets. To improve the understanding of public opinions and communication strategies, this paper presents MultiClimate, the first open-source manually-annotated stance detection dataset with $100$ CC-related YouTube videos and $4,209$ frame-transcript pairs. We deploy state-of-the-art vision and language models, as well as multimodal models for MultiClimate stance detection. Results show that text-only BERT significantly outperforms image-only ResNet50 and ViT. Combining both modalities achieves state-of-the-art, $0.747$/$0.749$ in accuracy/F1. Our 100M-sized fusion models also beat CLIP and BLIP, as well as the much larger 9B-sized multimodal IDEFICS and text-only Llama3 and Gemma2, indicating that multimodal stance detection remains challenging for large language models. Our code, dataset, as well as supplementary materials, are available at https://github.com/werywjw/MultiClimate.
arXiv.org Artificial Intelligence
Sep-26-2024
- Country:
- Oceania
- North America
- Saint Lucia (0.04)
- Greenland (0.04)
- Canada (0.04)
- Belize (0.04)
- United States
- Maryland (0.04)
- Colorado (0.04)
- New York > Erie County
- Buffalo (0.04)
- Nevada > Clark County
- Las Vegas (0.04)
- Minnesota > Hennepin County
- Minneapolis (0.14)
- Louisiana > Orleans Parish
- New Orleans (0.04)
- California > San Diego County
- San Diego (0.04)
- Europe
- Middle East > Malta (0.04)
- Austria (0.04)
- Spain > Andalusia
- Seville Province > Seville (0.04)
- Ireland > Leinster
- County Dublin > Dublin (0.04)
- Germany > Bavaria
- Upper Bavaria > Munich (0.04)
- Denmark > Capital Region
- Copenhagen (0.04)
- Asia
- Singapore (0.04)
- Philippines (0.04)
- Macao (0.04)
- Indonesia (0.04)
- China (0.04)
- Thailand > Bangkok
- Bangkok (0.04)
- Taiwan > Taiwan Province
- Taipei (0.04)
- Bangladesh > Dhaka Division
- Dhaka District > Dhaka (0.04)
- Africa
- West Africa (0.04)
- Tanzania (0.04)
- Sierra Leone (0.04)
- Middle East > Somalia (0.04)
- Genre:
- Research Report > New Finding (0.48)
- Industry:
- Information Technology (1.00)
- Energy (1.00)
- Food & Agriculture > Agriculture (0.93)
- Health & Medicine > Therapeutic Area
- Technology: