A social context-aware graph-based multimodal attentive learning framework for disaster content classification during emergencies: a benchmark dataset and method
This addresses the challenge for humanitarian organizations in efficiently leveraging multimodal social media data during emergencies, though it appears incremental as it builds on existing classification methods.
The paper tackled the problem of classifying disaster-related social media content by proposing CrisisSpot, a method that integrates graph-based neural networks and social context features, achieving an average F1-score gain of 9.45% on the CrisisMMD dataset and 5.01% on their new TSEqD dataset.
In times of crisis, the prompt and precise classification of disaster-related information shared on social media platforms is crucial for effective disaster response and public safety. During such critical events, individuals use social media to communicate, sharing multimodal textual and visual content. However, due to the significant influx of unfiltered and diverse data, humanitarian organizations face challenges in leveraging this information efficiently. Existing methods for classifying disaster-related content often fail to model users' credibility, emotional context, and social interaction information, which are essential for accurate classification. To address this gap, we propose CrisisSpot, a method that utilizes a Graph-based Neural Network to capture complex relationships between textual and visual modalities, as well as Social Context Features to incorporate user-centric and content-centric information. We also introduce Inverted Dual Embedded Attention (IDEA), which captures both harmonious and contrasting patterns within the data to enhance multimodal interactions and provide richer insights. Additionally, we present TSEqD (Turkey-Syria Earthquake Dataset), a large annotated dataset for a single disaster event, containing 10,352 samples. Through extensive experiments, CrisisSpot demonstrated significant improvements, achieving an average F1-score gain of 9.45% and 5.01% compared to state-of-the-art methods on the publicly available CrisisMMD dataset and the TSEqD dataset, respectively.