Who is the Hero, the Villain, and the Victim? Detection of Roles in News Articles using Natural Language Techniques

News articles often use narrative frames to present people, organizations, and facts. These narrative frames follow cultural archetypes, enabling readers to associate each of the presented elements with familiar stereotypes, wellknown characters, and recognizable outcomes. In this way, authors can cast real people or organizations as heroes, villains, or victims. We present a system that identifies the main entities of a news article, and determines which is being cast as a hero, a villain, or a victim. As currently implemented, this system interacts directly with news consumers through a browser extension. Our hope is that by informing readers when an entity is cast in one of these roles, we can make implicit bias explicit, and thereby assist readers in applying their media literacy skills. This approach can also be used to identify roles in well understood event sequences in a more prosaic manner, e.g., for information extraction.