Continuation Support of Conversation by Recommending Next Topics Relating to a Present Topic
Wataru Sunayama, Yuki Shibata, Yoko Nishihara · 2016
This paper proposes a conversation support system that recommends next topics relating to the present topic. The purpose of the proposed system is to support to continue conversation. The proposed system detects spoken words of two users, makes a log text of conversation. Then, the system extracts the present topic from the log text of conversation, and evaluates the relations between the present topic and next topic candidates. The system chooses next topics and recommends them to the users. The proposed system has an interface of Head Mounted Display (HMD) showing a log text of conversation, a word of the present topic, and words of the next topic. One of the users wearing the HMD can grasp what topic is talked, and choose a next topic from recommended them. The users can continue conversations by talking about recommended topics. Experimental results showed that the proposed system could support to continue conversations. We also found that the proposed system supported users to obtain equal chances to speak.