RESUMO
The uncertain check-ins bring challenges for current static next point-of-interest (POI) recommendation methods. Fortunately, the conversation-based recommendation has been shown the merit of integrating immediate user preference for more accurate recommendations. We, therefore, propose a conversation-based adaptive relational translation (CART) approach for the next POI recommendation over uncertain check-ins. It is equipped with recommender and conversation modules to interactively acquire users' immediate preferences and make dynamic recommendations. Specifically, the recommender built upon the adaptive relational translation method performs location prediction via modeling both users' historical sequential behaviors and the immediate preference received from conversations; the conversation module aims to achieve successful recommendations in fewer conversation turns by learning a conversational strategy, whereby the recommender can be updated via the user response. Extensive experiments on four real-world datasets show the superiority of our proposed CART over the state of the arts.
