To solve the problems of large data sparsity and lack of negative samples in most point of interest (POI) recommendation methods, a POI recommendation method based on deep learning in locationâbased social networks is proposed. Firstly, a bidirectional longâshortâterm memory (BiâLSTM) attention mechanism is designed to give different weights to different parts of the current sequence according to usersâ longâterm and shortâterm preferences. Then, the POI recommendation model is constructed, the sequence state data of the encoder is input into BiâLSTMâAttention to get the attention representation of the current POI checkâin sequence, and the TopâN recommendation list is generated after the decoder processing. Finally, a negative sampling method is proposed to obtain an effective negative sample set, which is used to improve the calculation of the Bayesian personalized ranking loss function. The proposed method is demonstrated experimentally on Foursquare and Gowalla datasets. The experimental results show that the proposed method has better accuracy, recall, and F1 value than other comparison methods.