Stance Prediction for Contemporary Issues: Data and Experiments
This work addresses stance detection for researchers and practitioners in NLP, but it is incremental as it builds on existing methods with a new dataset and minor enhancements.
The paper tackled stance detection in long discussions of contemporary issues by creating a novel dataset covering 419 controversial issues and showing that a shallow recurrent neural network with sentiment or emotion information achieves competitive results compared to fine-tuned BERT with 20x fewer parameters.
We investigate whether pre-trained bidirectional transformers with sentiment and emotion information improve stance detection in long discussions of contemporary issues. As a part of this work, we create a novel stance detection dataset covering 419 different controversial issues and their related pros and cons collected by procon.org in nonpartisan format. Experimental results show that a shallow recurrent neural network with sentiment or emotion information can reach competitive results compared to fine-tuned BERT with 20x fewer parameters. We also use a simple approach that explains which input phrases contribute to stance detection.