A General Framework for Domain-Specialization of Stance Detection

A Covid-19 Response Use Case

Authors

  • Brodie Mather IHMC
  • Bonnie J Dorr, Dr. IHMC
  • Owen Rambow, Dr. Stony Brook University
  • Tomek Strzalkowski, Dr. Rensselaer Polytechnic Institute

DOI:

https://doi.org/10.32473/flairs.v34i1.128457

Keywords:

stance, stance detection, covid, dependency parsing, semantic role labeling, belief, belief strength, sentiment, attitude

Abstract

We present a generalized framework for domain-specialized stance detection, focusing on Covid-19 as a use case. We define a stance as a predicate-argument structure (combination of an action and its participants) in a simplified one-argument format, e.g., wear(a mask), coupled with a task-specific belief category representing the purpose (e.g., protection) of an argument (e.g., mask) in the context of its predicate (e.g., wear), as constrained by the domain (e.g., Covid-19). A belief category PROTECT captures a belief such as “masks provide protection,” whereas RESTRICT captures a belief such as “mask mandates limit freedom.” A stance combines a belief proposition, e.g., PROTECT(wear(a mask)), with a sentiment toward this proposition. From this, an overall positive attitude toward mask wearing is extracted. The notions purpose and function serve as natural constraints on the choice of belief categories during resource building which, in turn, constrains stance detection. We demonstrate that linguistic constraints (e.g., light verb processing) further refine the choice of predicate-argument pairings for belief and sentiment assignments, yielding significant increases in F1 score for stance detection over a strong baseline.

Downloads

Published

2021-04-18

How to Cite

Mather, B., Dorr, B. J., Rambow, O., & Strzalkowski, T. (2021). A General Framework for Domain-Specialization of Stance Detection: A Covid-19 Response Use Case. The International FLAIRS Conference Proceedings, 34. https://doi.org/10.32473/flairs.v34i1.128457

Issue

Section

Special Track: Applied Natural Language Processing