Graph-based Features for Automatic Online Abuse Detection - Archive ouverte HAL Access content directly
Conference Papers Year : 2017

Graph-based Features for Automatic Online Abuse Detection

(1) , (1) , (1) , (1)
1

Abstract

While online communities have become increasingly important over the years, the moderation of user-generated content is still performed mostly manually. Automating this task is an important step in reducing the financial cost associated with moderation, but the majority of automated approaches strictly based on message content are highly vulnerable to intentional obfuscation. In this paper, we discuss methods for extracting conversational networks based on raw multi-participant chat logs, and we study the contribution of graph features to a classification system that aims to determine if a given message is abusive. The conversational graph-based system yields unexpectedly high performance , with results comparable to those previously obtained with a content-based approach.
Fichier principal
Vignette du fichier
main.pdf (870.73 Ko) Télécharger le fichier
Vignette du fichier
after-1.pdf (4.69 Ko) Télécharger le fichier
Vignette du fichier
all.pdf (495.04 Ko) Télécharger le fichier
Vignette du fichier
all_pr.pdf (157.41 Ko) Télécharger le fichier
Vignette du fichier
before-1.pdf (4.85 Ko) Télécharger le fichier
Vignette du fichier
full-1.pdf (5.07 Ko) Télécharger le fichier
Vignette du fichier
presentation.pdf (2.33 Mo) Télécharger le fichier
Origin : Files produced by the author(s)
Origin : Files produced by the author(s)
Origin : Files produced by the author(s)
Origin : Files produced by the author(s)
Origin : Files produced by the author(s)
Origin : Files produced by the author(s)

Dates and versions

hal-01571639 , version 1 (03-08-2017)

Licence

Attribution - NonCommercial - ShareAlike - CC BY 4.0

Identifiers

Cite

Etienne Papegnies, Vincent Labatut, Richard Dufour, Georges Linares. Graph-based Features for Automatic Online Abuse Detection. 5th International Conference on Statistical Language and Speech Processing, Oct 2017, Le Mans, France. pp.70-81, ⟨10.1007/978-3-319-68456-7_6⟩. ⟨hal-01571639⟩

Collections

UNIV-AVIGNON LIA
159 View
405 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More