Two Birds with One Stone: Improving Rumor Detection by Addressing the Unfairness Issue

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chen, Junyi, Wu, Mengjia, Liu, Qian, Ding, Ying, Zhang, Yi
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912172328615936
author Chen, Junyi
Wu, Mengjia
Liu, Qian
Ding, Ying
Zhang, Yi
author_facet Chen, Junyi
Wu, Mengjia
Liu, Qian
Ding, Ying
Zhang, Yi
contents The degraded performance and group unfairness caused by confounding sensitive attributes in rumor detection remains relatively unexplored. To address this, we propose a two-step framework. Initially, it identifies confounding sensitive attributes that limit rumor detection performance and cause unfairness across groups. Subsequently, we aim to learn equally informative representations through invariant learning. Our method considers diverse sets of groups without sensitive attribute annotations. Experiments show our method easily integrates with existing rumor detectors, significantly improving both their detection performance and fairness.
format Preprint
id arxiv_https___arxiv_org_abs_2412_20671
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Two Birds with One Stone: Improving Rumor Detection by Addressing the Unfairness Issue
Chen, Junyi
Wu, Mengjia
Liu, Qian
Ding, Ying
Zhang, Yi
Social and Information Networks
Machine Learning
The degraded performance and group unfairness caused by confounding sensitive attributes in rumor detection remains relatively unexplored. To address this, we propose a two-step framework. Initially, it identifies confounding sensitive attributes that limit rumor detection performance and cause unfairness across groups. Subsequently, we aim to learn equally informative representations through invariant learning. Our method considers diverse sets of groups without sensitive attribute annotations. Experiments show our method easily integrates with existing rumor detectors, significantly improving both their detection performance and fairness.
title Two Birds with One Stone: Improving Rumor Detection by Addressing the Unfairness Issue
topic Social and Information Networks
Machine Learning
url https://arxiv.org/abs/2412.20671