In recent years, successive Point-of-Interest (POI) recommendation has attracted more and more attention and many methods have been proposed to address the problem of successive POI recommendation. In this paper, we propose the SPENT method which uses similarity tree to organize all POIs and applies Word2Vec to perform POI embedding. Then, SPENT uses a recurrent neural network (RNN) to model users' successive transition behavior. We also propose to insert a bath normalization layer in front of the LSTM and a temporal distance gate in the back of the LSTM to improve the performance of SPENT. To compare the performance of SPENT and other prior successive POI recommendation methods, several experiments are conducted on two real datasets, Gowalla and Foursquare. Experimental results show that SPENT outperforms the other prior methods in terms of precision and recall.