Paper Info
Title
Graph-Based Features for Automatic Online Abuse Detection.
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.
Year
DOI
Venue
2017
10.1007/978-3-319-68456-7_6
SLSP
DocType
Volume
ISSN
Journal
abs/1708.01060
5th International Conference on Statistical Language and Speech Processing (SLSP), 2017, Le Mans (FR), Lecture Notes in Artificial Intelligence vol.10583, p.70-81
Citations 
PageRank 
References 
3
0.37
11
Authors
4
Name
Order
Citations
PageRank
Etienne Papegnies140.77
Vincent Labatut222727.37
richard dufour39823.98
georges linar es413629.55