SOTAVerified

Annotation and Detection of Arguments in Tweets

2020-12-01COLING (ArgMining) 2020Code Available0· sign in to hype

Robin Schaefer, Manfred Stede

Code Available — Be the first to reproduce this paper.

Reproduce

Code

Abstract

Notwithstanding the increasing role Twitter plays in modern political and social discourse, resources built for conducting argument mining on tweets remain limited. In this paper, we present a new corpus of German tweets annotated for argument components. To the best of our knowledge, this is the first corpus containing not only annotated full tweets but also argumentative spans within tweets. We further report first promising results using supervised classification (F1: 0.82) and sequence labeling (F1: 0.72) approaches.

Tasks

Reproductions