Argumentative Topology: Finding Loop(holes) in Logic

ARXIV’20 | Using persistent homology on word embeddings to find circles in circular arguments.

TL;DR

This work came out of a collaboration during my time as a Research Associate at Pacific Northwest National Laboratory. In the paper, we present a proof-of-concept framework for considering how to extract topological information from text data corresponding to different logical argument structures, originally motivated by the question “Why do we call a circular argument ‘circular’?” Checkout the paper here to learn more.