If there's a Trigger Warning, then where's the Trigger? Investigating Trigger Warnings at the Passage Level

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Wiegmann, Matti, Rakete, Jennifer, Wolska, Magdalena, Stein, Benno, Potthast, Martin
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866913315091906560
author Wiegmann, Matti
Rakete, Jennifer
Wolska, Magdalena
Stein, Benno
Potthast, Martin
author_facet Wiegmann, Matti
Rakete, Jennifer
Wolska, Magdalena
Stein, Benno
Potthast, Martin
contents Trigger warnings are labels that preface documents with sensitive content if this content could be perceived as harmful by certain groups of readers. Since warnings about a document intuitively need to be shown before reading it, authors usually assign trigger warnings at the document level. What parts of their writing prompted them to assign a warning, however, remains unclear. We investigate for the first time the feasibility of identifying the triggering passages of a document, both manually and computationally. We create a dataset of 4,135 English passages, each annotated with one of eight common trigger warnings. In a large-scale evaluation, we then systematically evaluate the effectiveness of fine-tuned and few-shot classifiers, and their generalizability. We find that trigger annotation belongs to the group of subjective annotation tasks in NLP, and that automatic trigger classification remains challenging but feasible.
format Preprint
id arxiv_https___arxiv_org_abs_2404_09615
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle If there's a Trigger Warning, then where's the Trigger? Investigating Trigger Warnings at the Passage Level
Wiegmann, Matti
Rakete, Jennifer
Wolska, Magdalena
Stein, Benno
Potthast, Martin
Computation and Language
Computers and Society
Trigger warnings are labels that preface documents with sensitive content if this content could be perceived as harmful by certain groups of readers. Since warnings about a document intuitively need to be shown before reading it, authors usually assign trigger warnings at the document level. What parts of their writing prompted them to assign a warning, however, remains unclear. We investigate for the first time the feasibility of identifying the triggering passages of a document, both manually and computationally. We create a dataset of 4,135 English passages, each annotated with one of eight common trigger warnings. In a large-scale evaluation, we then systematically evaluate the effectiveness of fine-tuned and few-shot classifiers, and their generalizability. We find that trigger annotation belongs to the group of subjective annotation tasks in NLP, and that automatic trigger classification remains challenging but feasible.
title If there's a Trigger Warning, then where's the Trigger? Investigating Trigger Warnings at the Passage Level
topic Computation and Language
Computers and Society
url https://arxiv.org/abs/2404.09615