Model of Multi-turn Dialogue in Emotional Chatbot

The intent recognition and natural language understanding of multi-turn dialogue is key for the commercialization of chatbots. Chatbots are mainly used for the processing of specific tasks, and can introduce products to customers or solve related problems, thus saving human resources. Text sentiment recognition enables a chatbot to know the user’s emotional state and select the best response, which is important in medical care. In this study, we combined the multi-turn dialogue model and sentiment recognition model to develop a chatbot, that is designed for used in daily conversations rather than for specific tasks. Thus, the chatbot has the ability to provide the robot’s emotions as feedback while talking with a user. Moreover, it can exhibit different emotional reactions based on the content of the user’s conversation.