3.8 Proceedings Paper

Disentangled Learning of Stance and Aspect Topics for Vaccine Attitude Detection in Social Media

Publisher

ASSOC COMPUTATIONAL LINGUISTICS-ACL

Keywords

-

Funding

  1. UK Engineering and Physical Sciences Research Council [EP/T017112/1, EP/V048597/1]
  2. Chancellor's International Scholarship at the University of Warwick
  3. Turing AI Fellowship - UK Research and Innovation [EP/V020579/1]

Ask authors/readers for more resources

Building models to detect vaccine attitudes on social media is challenging due to the complexity and limited availability of annotated data. This study proposes a novel semi-supervised approach called VADET, which leverages unannotated data to learn the topical information of the domain, and fine-tunes the model with manually annotated examples. The results demonstrate that VADET outperforms existing models in 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. Our source code and dataset are available at http://github.com/somethingx1202/VADet.

Authors

I am an author on this paper
Click your name to claim this paper and add it to your profile.

Reviews

Primary Rating

3.8
Not enough ratings

Secondary Ratings

Novelty
-
Significance
-
Scientific rigor
-
Rate this paper

Recommended

No Data Available
No Data Available