With the goal of building an intelligent conversational agent that can recognize the user's engagement, this paper proposes a method of judging a user's conversational engagement based on head pose data. First, we analyzed how head pose information is correlated with the user's conversational engagement and found that the amplitude of head movement and rotation have a moderate positive correlation with the level of conversational engagement. We then established an engagement estimation model by applying a decision tree learning algorithm to 19 parameters. The results showed that the proposed model based on head pose information performs quite well.