No Time like the Present: Effects of Language Change on Automated Comment Moderation

Justen, Lennart; Müller, Kilian; Niemann, Marco; Becker, Jörg


Abstract

The spread of online hate has become a significant problem for newspapers that host comment sections. As a result, there is growing interest in using machine learning and natural language processing for (semi-) automated abusive language detection to avoid manual comment moderation costs or having to shut down comment sections altogether. However, much of the past work on abusive language detection assumes that classifiers operate in a static language environment, despite language and news being in a state of constant flux. In this paper, we show using a new German newspaper comments dataset that the classifiers trained with naive ML techniques like a random-test train split will underperform on future data, and that a time stratified evaluation split is more appropriate. We also show that classifier performance rapidly degrades when evaluated on data from a different period than the training data. Our findings suggest that it is necessary to consider the temporal dynamics of language when developing an abusive language detection system or risk deploying a model that will quickly become defunct.

Keywords
abusive language detection; natural language processing; concept drift; Auto-ML; COVID-19



Publication type
Forschungsartikel in Sammelband (Konferenz)

Peer reviewed
Yes

Publication status
Published

Year
2022

Conference
Conference on Business Informatics

Venue
Amsterdam

Book title
Proceedings of the Conference on Business Informatics 2022

Editor
Poels, Geert; da Silva, Miguel Mira; de Kinderen, Sybren; Sales, Tiaga Prince; Gordijn, Jaap

Start page
40

End page
50

Publisher
Wiley-IEEE Computer Society Press

Place
Online

Language
English

DOI