Not All Comments are Equal: Insights into Comment Moderation from a Topic-Aware Model

TL;DR

This paper presents a topic-aware comment moderation model that leverages semantic features to improve accuracy and interpretability, addressing the variability of comment content across different news sections.

Contribution

The study introduces a novel topic-aware approach for comment moderation that enhances classification performance and interpretability by integrating semantic features from topic models.

Findings

Topic-aware models outperform non-topic-aware baselines.

Incorporating semantic features increases model confidence.

Content varies significantly across different news sections.

Abstract

Moderation of reader comments is a significant problem for online news platforms. Here, we experiment with models for automatic moderation, using a dataset of comments from a popular Croatian newspaper. Our analysis shows that while comments that violate the moderation rules mostly share common linguistic and thematic features, their content varies across the different sections of the newspaper. We therefore make our models topic-aware, incorporating semantic features from a topic model into the classification decision. Our results show that topic information improves the performance of the model, increases its confidence in correct outputs, and helps us understand the model's outputs.