(Mis) alignment between stance expressed in social media data and public opinion surveys

K Joseph, S Shugars, R Gallagher, J Green… - arXiv preprint arXiv …, 2021 - arxiv.org
Stance detection, which aims to determine whether an individual is for or against a target
concept, promises to uncover public opinion from large streams of social media data. Yet …

Debiased label aggregation for subjective crowdsourcing tasks

S Wallace, T Cai, B Le, LA Leiva - CHI Conference on Human Factors in …, 2022 - dl.acm.org
Human Intelligence Tasks (HITs) allow people to collect and curate labeled data from
multiple annotators. Then labels are often aggregated to create an annotated dataset …

You are what you tweet: Profiling users by past tweets to improve hate speech detection

P Chaudhry, M Lease - International Conference on Information, 2022 - Springer
Hate speech detection research has predominantly focused on purely content-based
methods, without exploiting other contextual data. We briefly critique pros and cons of this …