Machine Learning Can Automatically Flag Risky Instagram Conversations, Finds New Study

A new study has found a way to use machine learning to flag risky conversations on Instagram without eavesdropping on them. Researchers from four leading universities analyzed data inputs, including metadata attributes, texts, and image features, to train machine learning models for identifying risky conversations. The program was able to identify risky conversations with 87% accuracy using only these sparsely available and anonymous details. The team's system offers a two-way solution that can protect young users while also maintaining their privacy.