Understanding Human and Predictive Moderation of Online Science Discourse

Abstract

Manual moderation activities can be fatiguing, emotionally exhausting, and potentially traumatizing, yet moderation is essential to the health of the discussion community. Communities, therefore, can benefit from automated moderation systems. We report on a study with a survey about moderation behaviors and an annotation task involving forum comments to aid curating a deeper understanding of moderation towards predictive support. We also create models for distinguishing between acceptable and unacceptable scientific forum comments and discuss results given moderators responses.