Identification of Multimodal Stance Towards Frames of Communication
Maxwell A. Weinzierl, Sanda M. Harabagiu
摘要
Frames of communication are often evoked in multimedia documents. When an author decides to add an image to a text, one or both of the modalities may evoke a communication frame. Moreover, when evoking the frame, the author also conveys her/his stance towards the frame. Until now, determining if the author is in favor of, against or has no stance towards the frame was performed automatically only when processing texts. This is due to the absence of stance annotations on multimedia documents. In this paper we introduce MMVAX-STANCE, a dataset of 11,300 multimedia documents retrieved from social media, which have stance annotations towards 113 different frames of communication. This dataset allowed us to experiment with several models of multimedia stance detection, which revealed important interactions between texts and images in the inference of stance towards communication frames. When inferring the text/image relations, a set of 46,606 synthetic examples of multimodal documents with known stance was generated. This greatly impacted the quality of identifying multimedia stance, yielding an improvement of 20% in F1-score. Component Definition Examples of Frames of Communication Confidence Trust in the security and effectiveness of 2 Pfizer COVID-19 vaccine may cause anaphylaxis vaccinations, the health authorities, and in people with polyethylene glycol (PEG) allergy. the health officials who recommend 2 The Government has provided plenty of safety and develop vaccines. information about the COVID-19 vaccines. Complacency Complacency and laziness to get vaccinated 2 Preference for getting COVID-19 and fighting due to low perceived risk of infections. it off than vaccinating. Constraints Structural or psychological hurdles that 2 It takes courage both to vaccinate against make vaccination difficult or costly. COVID-19 and to refuse the vaccine. Calculation Degree to which personal costs and benefits 2 COVID-19 vaccines protect against the emerging of vaccination are weighted. variants. Collective Willingness to protect others and to 2 Vaccination is key in protecting yourself and others Responsibility eliminate infectious diseases. against COVID-19. Compliance Support for societal monitoring and sanctioning 2 People choosing not to get the COVID-19 vaccine of people who are not vaccinated. should not lose venue access/travel to some countries. Conspiracy Conspiracy thinking and belief in 2 COVID-19 vaccines make you 5G compatible. fake news related to vaccination. 2 The COVID vaccine renders pregnancies risky.
问问这篇 Paper
智能体会读完全文。
Lune 把这篇 Paper 索引到了每一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。
引用它的顶会 Paper4
- Multimodal Multi-turn Conversation Stance Detection: A Challenge Dataset and Effective ModelFuqiang Niu, Zebang Cheng, Xianghua Fu, Xiaojiang Peng 等ACM MM 2024 · 被引用 13 次
- Exploring Artificial Image Generation for Stance DetectionZhengkang Zhang, Zhongqing Wang, Guodong ZhouEMNLP 2025
- T-MAD: Target-driven Multimodal Alignment for Stance DetectionZhaoDan Zhang, Jin Zhang, Xueqi Cheng, Hui XuEMNLP 2025
- Multimodal Coreference Resolution for Chinese Social Media Dialogues: Dataset and Benchmark ApproachXingyu Li, Chen Gong, Guohong FuACL 2025
它引用的顶会 Paper7
- Learning Transferable Visual Models From Natural Language SupervisionAlec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh 等ICML 2021 · 被引用 47,906 次
- BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language ModelsJunnan Li, Dongxu Li, Silvio Savarese, Steven C. H. HoiICML 2023 · 被引用 7,873 次
- ViLT: Vision-and-Language Transformer Without Convolution or Region SupervisionWonjae Kim, Bokyung Son, Ildoo KimICML 2021 · 被引用 2,258 次
- FLAVA: A Foundational Language And Vision Alignment ModelAmanpreet Singh, Ronghang Hu, Vedanuj Goswami, Guillaume Couairon 等CVPR 2022 · 被引用 483 次
- BridgeTower: Building Bridges between Encoders in Vision-Language Representation LearningXiao Xu, Chenfei Wu, Shachar Rosenman, Vasudev Lal 等AAAI 2023 · 被引用 99 次
相关 Paper
- Mitigating World Biases: A Multimodal Multi-View Debiasing Framework for Fake News Video DetectionZhi Zeng, Minnan Luo, Xiangzheng Kong, Huan Liu 等ACM MM 2024 · 被引用 43 次
- Identifying the Adoption or Rejection of Misinformation Targeting COVID-19 Vaccines in Twitter DiscourseMaxwell A. Weinzierl, Sanda M. HarabagiuWWW 2022 · 被引用 19 次
- Edited Media Understanding Frames: Reasoning About the Intent and Implications of Visual MisinformationJeff Da, Maxwell Forbes, Rowan Zellers, Anthony Zheng 等ACL 2021
- Generating Multimodal Metaphorical Features for Meme UnderstandingBo Xu, Junzhe Zheng, Jiayuan He, Yuxuan Sun 等ACM MM 2024 · 被引用 6 次
- Stance Detection in COVID-19 TweetsKyle Glandt, Sarthak Khanal, Yingjie Li, Doina Caragea 等ACL 2021
