Online misbehavior such as stalking, doxxing, inappropriate messages, is prevalent on mobile applications. We observed that app users report such incidents in the app reviews. Victims of such incidents are intimidated and feel unsafe on the apps. App developers and the app distribution stores should be aware of such incidents, and take actions to rectify the misuse problem. We explored multiple Natural Language Processing (NLP) techniques to identify such incidents from the app reviews data set. Our best model achieved 80.63% precision at 73.48% recall.

Sanjana Cheerla is a fourth-year computer science student at North Carolina State University. She is working towards her bachelor’s degree and after graduating this May, she will be pursuing higher education for a master’s degree also in computer science. Her primary focus in research is on using AI/NLP techniques for social good.