Abstract
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.- Anthology ID:
- 2020.socialnlp-1.5
- Volume:
- Proceedings of the Eighth International Workshop on Natural Language Processing for Social Media
- Month:
- July
- Year:
- 2020
- Address:
- Online
- Venue:
- SocialNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 32–40
- Language:
- URL:
- https://aclanthology.org/2020.socialnlp-1.5
- DOI:
- 10.18653/v1/2020.socialnlp-1.5
- Cite (ACL):
- Marjan Hosseinia, Eduard Dragut, and Arjun Mukherjee. 2020. Stance Prediction for Contemporary Issues: Data and Experiments. In Proceedings of the Eighth International Workshop on Natural Language Processing for Social Media, pages 32–40, Online. Association for Computational Linguistics.
- Cite (Informal):
- Stance Prediction for Contemporary Issues: Data and Experiments (Hosseinia et al., SocialNLP 2020)
- PDF:
- https://preview.aclanthology.org/ingestion-script-update/2020.socialnlp-1.5.pdf
- Code
- marjanhs/procon20
- Data
- Procon20