Applying the Character-Based Chatbots Generation Framework in Education and Healthcare
Walid El Hefny, Alia El Bolock, Cornelia Herbert, Slim Abdennadher
Abstract
Users have different expectations while interacting with chatbots. However, current chatbots do not consider the users’ preferences and needs, creating unpleasant biases towards certain user groups. User characteristics play a vital role in predicting preferences and thus eliciting better responses as advocated by Character Computing. A framework was proposed in the literature to build character-based chatbots with adjustable traits. In this paper, we customize the framework modules to build two chatbots for different domains using the same set of chatbot characters. First, we present a character-based chatbot for academic support. It provides students with information regarding the content, dates, timings, locations, and deadlines of their courses. Second, we present a character-based chatbot for COVID-19. It provides users with answers to frequently asked questions, advice and precautions, cases per country, and symptoms checking. Users can select their preferable chatbot character to interact with, and receive personalized responses accordingly. Moreover, we investigated the prediction of a user’s favorite chatbot character based on their personality traits to create adaptable chatbots in the future. Finally, we investigated the effect of a chatbot’s character on its likability and trustworthiness.