Can We Automate the Analysis of Online Child Sexual Exploitation Discourse?
This work addresses online child safety by automating detection of grooming behaviors, but it is incremental as it shows models are not yet on-par with human experts.
The study tackled the problem of detecting predatory behaviors in online child sexual exploitation discourse by testing automated classification methods on 6,772 chat messages labeled with 11 behaviors, finding that the best models performed consistently but not as well as human annotation.
Social media's growing popularity raises concerns around children's online safety. Interactions between minors and adults with predatory intentions is a particularly grave concern. Research into online sexual grooming has often relied on domain experts to manually annotate conversations, limiting both scale and scope. In this work, we test how well-automated methods can detect conversational behaviors and replace an expert human annotator. Informed by psychological theories of online grooming, we label $6772$ chat messages sent by child-sex offenders with one of eleven predatory behaviors. We train bag-of-words and natural language inference models to classify each behavior, and show that the best performing models classify behaviors in a manner that is consistent, but not on-par, with human annotation.