Abstract

Persuasion is becoming a hot topic for intelligent interfaces. As opposed to traditional scenarios where User Interfaces are meant to give control to the user, future intelligent systems may have contextual goals to pursue. They may aim at inducing the user, or in general, the audience, to perform a specific action in the real world, change attitudes or beliefs, etc. These systems will have to take into account the social environment, exploit the situational context, and enhance emotional aspects in communication. In this paper, we will focus on Natural Language Generation (NLG) of persuasive messages, not necessarily based on argumentation. The aim of the paper is to provide an overview of systems that realize some reasoning mechanisms about the effectiveness of the message. We will conclude with some emerging trends in the field.