Host: The Japanese Society for Artificial Intelligence
Name : 34th Annual Conference, 2020
Number : 34
Location : Online
Date : June 09, 2020 - June 12, 2020
In this paper, we propose a method that a conversational agent autonomously controls linguistic consideration (politeness). As an approach to realize the proposed method, we examined input information based on politeness theory in sociolinguistics that is considered to be effective for agents to control politeness. Result of the examine, smooth communication becomes possible by the agent performs that politeness control taking into account the social relationship with the user based on utilizing the user's attribute information such as gender/age, and the degree of formalness and culture on the conversation scene. Also, in this paper, we report the results of experiments that verify how politeness is controlled based on the three factors of social distance/social status difference/conversation scene (culture) in human relationships.