In recent years, chatbots have been empowered to engage in social conversations with humans and have the potential to elicit people to disclose their personal experiences, opinions, and emotions. However, how and to what extent people respond to chabots self-disclosure remain less known. In this work, we designed a social chatbot with three self-disclosure levels that conducted small talks and provided relevant recommendations to people. 372 MTurk participants were randomized to one of the four groups with different self-disclosure levels to converse with the chatbot on two topics, movies, and COVID-19. We found that peoples self-disclosure level was strongly reciprocal to a chatbots self-disclosure level. Chatbots self-disclosure also positively impacted engagement and users perception of the bot and led to a more effective recommendation such that participants enjoyed and agreed more with the recommendations.
Download