Stanford Seminar Thesis Defense: Smart Tutoring Through Conversational Interfaces

Sherry Ruan Stanford University In the wellknown two sigma problem introduced in 1984, Bloom found that students tutored by a oneonone expert tutor achieved a learning outcome two standard deviations higher than those taught using traditional classroom methods. Since oneonone tutoring is too costly to scale up to the majority of students, technologybased solutions have been suggested as promising solutions to simulate oneonone human tutoring experiences. However, current automated computerbased tutors still primarily consist of learning activities with limited interactivity such as multiplechoice questions, reviewandflip flash cards, and listenandrepeat practices. These tutors tend to be unengaging and thus their effectiveness typically relies on students desire to learn. With recent advances in artificial intelligence (AI), we now have the potential to create conversationbased tutoring systems with the ability to provide personalized feedback to make learning more engaging and effective and