Comparing users' perception of different chatbot interaction paradigms: A case study

Abstract

In this work, we used the results of applying the Semiotic Inspection Method (SIM) to popular chatbots[12, 13], which yielded eleven strategies for conveying features to users, as well as six sign classes used for designing their interaction. We conducted user studies comparing two prototype chatbots with same features and different approaches to interaction: one using Natural Language Processing, and other using the sign classes and strategies to guide the user interaction. After that, we interviewed the participants, asking about their preferred aspects of each chatbot and their opinions regarding some of these aspects, and, later, analyzed the results. These point to the effectiveness of the strategies and sign classes. Then, we discuss users' perceptions of different ways of interacting with chatbots and their communicative strategies.