CrisisKAN: Knowledge-infused and Explainable Multimodal Attention Network for Crisis Event Classification
This work addresses the problem of reliable and explainable crisis event classification for disaster and pandemic response, though it appears incremental as it builds on existing multimodal and explainable AI techniques.
The authors tackled the challenge of classifying crisis events from social media by addressing semantic gaps between image and text modalities, lack of explainability, and bias from word limits, proposing CrisisKAN which integrates external Wikipedia knowledge and a cross-attention module, and it outperforms state-of-the-art methods on the CrisisMMD dataset.
Pervasive use of social media has become the emerging source for real-time information (like images, text, or both) to identify various events. Despite the rapid growth of image and text-based event classification, the state-of-the-art (SOTA) models find it challenging to bridge the semantic gap between features of image and text modalities due to inconsistent encoding. Also, the black-box nature of models fails to explain the model's outcomes for building trust in high-stakes situations such as disasters, pandemic. Additionally, the word limit imposed on social media posts can potentially introduce bias towards specific events. To address these issues, we proposed CrisisKAN, a novel Knowledge-infused and Explainable Multimodal Attention Network that entails images and texts in conjunction with external knowledge from Wikipedia to classify crisis events. To enrich the context-specific understanding of textual information, we integrated Wikipedia knowledge using proposed wiki extraction algorithm. Along with this, a guided cross-attention module is implemented to fill the semantic gap in integrating visual and textual data. In order to ensure reliability, we employ a model-specific approach called Gradient-weighted Class Activation Mapping (Grad-CAM) that provides a robust explanation of the predictions of the proposed model. The comprehensive experiments conducted on the CrisisMMD dataset yield in-depth analysis across various crisis-specific tasks and settings. As a result, CrisisKAN outperforms existing SOTA methodologies and provides a novel view in the domain of explainable multimodal event classification.