Disentangled Learning of Stance and Aspect Topics for Vaccine Attitude Detection in Social Media
This addresses the problem of limited annotated data for vaccine attitude analysis on social media, offering a more efficient method for researchers and public health analysts, though it is incremental as it builds on existing semi-supervised and aspect-based sentiment analysis techniques.
The paper tackles vaccine attitude detection in social media by proposing VADet, a semi-supervised approach that uses a variational autoencoder to learn from unlabeled data and fine-tunes with few annotations, outperforming existing models on stance detection and tweet clustering.
Building models to detect vaccine attitudes on social media is challenging because of the composite, often intricate aspects involved, and the limited availability of annotated data. Existing approaches have relied heavily on supervised training that requires abundant annotations and pre-defined aspect categories. Instead, with the aim of leveraging the large amount of unannotated data now available on vaccination, we propose a novel semi-supervised approach for vaccine attitude detection, called VADet. A variational autoencoding architecture based on language models is employed to learn from unlabelled data the topical information of the domain. Then, the model is fine-tuned with a few manually annotated examples of user attitudes. We validate the effectiveness of VADet on our annotated data and also on an existing vaccination corpus annotated with opinions on vaccines. Our results show that VADet is able to learn disentangled stance and aspect topics, and outperforms existing aspect-based sentiment analysis models on both stance detection and tweet clustering.