The Persuasive Power of Human-Machine Dialogue

The persuasive power of live interaction is hard to match, yet technologies are increasingly taking on roles to promote behavioral change. We believe that speech-based interfaces offer a compelling mode of interaction for engaging users and are motivated to understand how to best present persuasive information using speech interaction. We present a study comparing the persuasive power of two speech-based information systems, one which uses a recorded message-based lecture presentation and another which uses an interactive dialogic presentation. We measure the persuasive power across both conditions using a survival task. We find that the dialogic system is significantly more persuasive than the lecture system. We also find that the dialogic system presents significantly (almost four times) less information than the lecture system. We analyze our results using three standard rank correlation methods. We point to limitations of these measures and propose a new metric which appears to be more sensitive for this task.