Explainable Abuse Detection as Intent Classification and Slot Filling

TL;DR

This paper introduces a policy-aware approach to abuse detection on social media, using intent classification and slot filling to align model predictions with moderation guidelines, improving interpretability and reliability.

Contribution

It presents a novel framework that incorporates moderation policies into abuse detection via intent and slot annotations, along with a new dataset of annotated social media posts.

Findings

Policy-aware models outperform traditional data-driven models in abuse detection.

Annotated dataset of 3,535 posts enables training of intent and slot-based classifiers.

Models provide interpretable rationales aligned with moderation policies.

Abstract

To proactively offer social media users a safe online experience, there is a need for systems that can detect harmful posts and promptly alert platform moderators. In order to guarantee the enforcement of a consistent policy, moderators are provided with detailed guidelines. In contrast, most state-of-the-art models learn what abuse is from labelled examples and as a result base their predictions on spurious cues, such as the presence of group identifiers, which can be unreliable. In this work we introduce the concept of policy-aware abuse detection, abandoning the unrealistic expectation that systems can reliably learn which phenomena constitute abuse from inspecting the data alone. We propose a machine-friendly representation of the policy that moderators wish to enforce, by breaking it down into a collection of intents and slots. We collect and annotate a dataset of 3,535 English posts with such slots, and show how architectures for intent classification and slot filling can be used for abuse detection, while providing a rationale for model decisions.