Domain Adaptation with Adversarial Training and Graph Embeddings
This work addresses the challenge of limited labeled data for crisis event classification on social media, offering a domain adaptation solution that is incremental in combining existing techniques.
The paper tackles the problem of classifying social media posts during crisis events by leveraging labeled and unlabeled data from past events, proposing a model that combines adversarial domain adaptation and graph-based semi-supervised learning to handle distribution shifts and utilize unlabeled data, with experiments on Twitter datasets showing significant improvements over baselines.
The success of deep neural networks (DNNs) is heavily dependent on the availability of labeled data. However, obtaining labeled data is a big challenge in many real-world problems. In such scenarios, a DNN model can leverage labeled and unlabeled data from a related domain, but it has to deal with the shift in data distributions between the source and the target domains. In this paper, we study the problem of classifying social media posts during a crisis event (e.g., Earthquake). For that, we use labeled and unlabeled data from past similar events (e.g., Flood) and unlabeled data for the current event. We propose a novel model that performs adversarial learning based domain adaptation to deal with distribution drifts and graph based semi-supervised learning to leverage unlabeled data within a single unified deep learning framework. Our experiments with two real-world crisis datasets collected from Twitter demonstrate significant improvements over several baselines.