Saved in:
Bibliographic Details
Main Authors: Paudel, Pujan, Saeed, Mohammad Hammas, Auger, Rebecca, Wells, Chris, Stringhini, Gianluca
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2407.20910
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913452699680768
author Paudel, Pujan
Saeed, Mohammad Hammas
Auger, Rebecca
Wells, Chris
Stringhini, Gianluca
author_facet Paudel, Pujan
Saeed, Mohammad Hammas
Auger, Rebecca
Wells, Chris
Stringhini, Gianluca
contents Automated soft moderation systems are unable to ascertain if a post supports or refutes a false claim, resulting in a large number of contextual false positives. This limits their effectiveness, for example undermining trust in health experts by adding warnings to their posts or resorting to vague warnings instead of granular fact-checks, which result in desensitizing users. In this paper, we propose to incorporate stance detection into existing automated soft-moderation pipelines, with the goal of ruling out contextual false positives and providing more precise recommendations for social media content that should receive warnings. We develop a textual deviation task called Contrastive Textual Deviation (CTD) and show that it outperforms existing stance detection approaches when applied to soft moderation.We then integrate CTD into the stateof-the-art system for automated soft moderation Lambretta, showing that our approach can reduce contextual false positives from 20% to 2.1%, providing another important building block towards deploying reliable automated soft moderation tools on social media.
format Preprint
id arxiv_https___arxiv_org_abs_2407_20910
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Enabling Contextual Soft Moderation on Social Media through Contrastive Textual Deviation
Paudel, Pujan
Saeed, Mohammad Hammas
Auger, Rebecca
Wells, Chris
Stringhini, Gianluca
Computation and Language
Cryptography and Security
Automated soft moderation systems are unable to ascertain if a post supports or refutes a false claim, resulting in a large number of contextual false positives. This limits their effectiveness, for example undermining trust in health experts by adding warnings to their posts or resorting to vague warnings instead of granular fact-checks, which result in desensitizing users. In this paper, we propose to incorporate stance detection into existing automated soft-moderation pipelines, with the goal of ruling out contextual false positives and providing more precise recommendations for social media content that should receive warnings. We develop a textual deviation task called Contrastive Textual Deviation (CTD) and show that it outperforms existing stance detection approaches when applied to soft moderation.We then integrate CTD into the stateof-the-art system for automated soft moderation Lambretta, showing that our approach can reduce contextual false positives from 20% to 2.1%, providing another important building block towards deploying reliable automated soft moderation tools on social media.
title Enabling Contextual Soft Moderation on Social Media through Contrastive Textual Deviation
topic Computation and Language
Cryptography and Security
url https://arxiv.org/abs/2407.20910