Mining Bipolar Argumentation Frameworks from Natural Language Text.
Oana Cocarascu, Francesca Toni · Spiral (Imperial College London) · 2017
We describe a methodology for mining topic-dependent Bipolar Argumentation Frameworks (BAFs) from natural language text. Our focus is on identifying attack and support argumentative re- lations between texts about the same topic, treating these texts as arguments when they are argumentatively related to other texts. We illustrate our methodology on a dataset of hotel reviews and outline some possible applications using the BAFs resulting from our methodology.