Audience aware computational discourse generation for instruction and persuasion
Eren Sila Sayan · DSpace@MIT (Massachusetts Institute of Technology) · 2014
If we are to take artificial intelligence to the next level, we must further our under-standing of human storytelling, arguably the most salient aspect of human intelli-gence. The idea that the study and understanding of human narrative capability can advance multiple fields, including artificial intelligence, isn't a new one. The follow-ing, however, is: I claim that the right way to study and understand storytelling is not through the traditional lens of human creativity, aesthetics or even as a plain planning problem, but through formulating storytelling as a question of goal driven social interaction. In particular, I claim that any theory of storytelling must account for the goals of the storyteller and the storyteller's audience. To take a step toward such an account, I offer a framework, which I call Audi-ence Aware Narrative Generation, drawing inspiration in particular from narratology, cognitive science, and of course, computer science. I propose questions that we need to work on answering, and suggest some rudimentary starter thoughts to serve as guidelines for continued research. I picked a small subset of the proposed questions