Sex, drugs, and violence
This addresses the need for scalable content moderation in user-generated online platforms, though it appears incremental as it builds on existing topic modeling techniques.
The paper tackled the problem of automatically detecting inappropriate content in online narratives by using a largely unsupervised approach with topic modeling and regression on a corpus from a self-publishing website, achieving recall up to 96% and low regression errors.
Automatically detecting inappropriate content can be a difficult NLP task, requiring understanding context and innuendo, not just identifying specific keywords. Due to the large quantity of online user-generated content, automatic detection is becoming increasingly necessary. We take a largely unsupervised approach using a large corpus of narratives from a community-based self-publishing website and a small segment of crowd-sourced annotations. We explore topic modelling using latent Dirichlet allocation (and a variation), and use these to regress appropriateness ratings, effectively automating rating for suitability. The results suggest that certain topics inferred may be useful in detecting latent inappropriateness -- yielding recall up to 96% and low regression errors.