2017/01/01 by Reuben Binns, Michael Veale, Max Van Kleek +1 · 77 citations
Computer Science · Social Sciences · #Affect (linguistics) #Computational and Text Analysis Methods #Conformity #Diversity (politics) #Hate Speech and Cyberbullying Detection #Inheritance (genetic algorithm) #Moderation #Normative #Offensive #Sentiment Analysis and Opinion Mining #Viewpoints #cs.CL #cs.CY #cs.LG
paper · pdf · doi:10.1007/978-3-319-67256-4_32
published in Lecture notes in computer science, 405-415 (Springer Science+Business Media) · 12 pages, 3 figures, 9th International Conference on Social Informatics (SocInfo 2017), Oxford, UK, 13--15 September 2017 (forthcoming in Springer Lecture Notes in Computer Science)
openalex publication_date 2017/01/01 · arxiv created 2017/07/05 · openalex created_date 2017/07/14 · arxiv updated 2017/09/06 · openalex updated_date 2026/08/05
The internet has become a central medium through which `networked publics' express their opinions and engage in debate. Offensive comments and personal attacks can inhibit participation in these spaces. Automated content moderation aims to overcome this problem using machine learning classifiers trained on large corpora of texts manually annotated for offence. While such systems could help encourage more civil debate, they must navigate inherently normatively contestable boundaries, and are subject to the idiosyncratic norms of the human raters who provide the training data. An important objective for platforms implementing such measures might be to ensure that they are not unduly biased towards or against particular norms of offence. This paper provides some exploratory methods by which the normative biases of algorithmic content moderation systems can be measured, by way of a case study using an existing dataset of comments labelled for offence. We train classifiers on comments labelled by different demographic subsets (men and women) to understand how differences in conceptions of offence between these groups might affect the performance of the resulting models on various test sets. We conclude by discussing some of the ethical choices facing the implementers of algorithmic moderation systems, given various desired levels of diversity of viewpoints amongst discussion participants.