HomeLREC 2026WorkshopsNLPERSPECTIVESlrec2026-ws-nlperspectives-06
Back to NLPERSPECTIVES 2026
LREC 2026workshop

A Measure of Systematic Disagreement

Proceedings of the the fifth edition of NLPerspectives

DOI:10.63317/45wnhb2svtqd

Abstract

We introduce a new metric that quantifies the extent of systematicity of the disagreement between annotators. The metric, called σ, is inspired by Structural Balance Theory and it approximates the clusterability of the annotators of a dataset. Paired with a standard metric of inter-annotator agreement such as Krippendorffs α, σ measures the amount of disagreement which stems from genuine subjective factors as opposed to the amount of disagreement caused by inner features of the annotation task. The metric is applied to over twenty datasets encoding a broad variety of annotations, showing its effectiveness in capturing the systematicity of annotator disagreement and its explanatory value.

Details

Paper ID
lrec2026-ws-nlperspectives-06
Pages
pp. 56-65
BibKey
basile-2026-measure
Editors
Shiran Dudy, Gavin Abercrombie, Valerio Basile, Elisa Leonardelli, Simona Frenda
Publisher
European Language Resources Association (ELRA)
ISSN
N/A
ISBN
N/A
Workshop
Proceedings of the the fifth edition of NLPerspectives
Location
Palma, Mallorca, Spain
Date
11 - 16 May 2026

Authors

  • VB

    Valerio Basile

Links