SASRM: A Semantic and Attention Spatio-temporal Recurrent Model for Next Location Prediction

Predicting user’s next location is of great importance for a wide spectrum of location-based applications. However, most prediction methods do not take advantage of the rich semantic information contained in trajectory data. Meanwhile, the traditional LSTM-based model can not capture the spatio-temporal dependencies well. In this paper, we propose a Semantic and Attention Spatio-temporal Recurrent Model (SASRM) for next location prediction. Firstly, the SASRM put forward a method for encoding semantic vectors and concatenating vectors (location, time and semantic vectors) as input to the model. To capture the spatio-temporal dependencies, we design a variant recurrent unit based on LSTM. Further, an attention layer is used to weight hidden state to capture the influence of the historical locations on the next location prediction. We perform experiments on two real-life semantic trajectory datasets, and evaluation results demonstrate that our model outperforms several state-of-the-art models in accuracy.

[1]  Lukás Burget,et al.  Extensions of recurrent neural network language model , 2011, 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[2]  Lei Deng,et al.  Building a Big Data Analytics Service Framework for Mobile Advertising and Marketing , 2015, 2015 IEEE First International Conference on Big Data Computing Service and Applications.

[3]  Yu Zheng,et al.  Trajectory Data Mining , 2015, ACM Trans. Intell. Syst. Technol..

[4]  Lidan Shou,et al.  Splitter: Mining Fine-Grained Sequential Patterns in Semantic Trajectories , 2014, Proc. VLDB Endow..

[5]  Duncan J. Watts,et al.  Everyone's an influencer: quantifying influence on twitter , 2011, WSDM '11.

[6]  Matthias Hein,et al.  Variants of RMSProp and Adagrad with Logarithmic Regret Bounds , 2017, ICML.

[7]  Yifeng Zeng,et al.  Personalized Ranking Metric Embedding for Next New POI Recommendation , 2015, IJCAI.

[8]  Lars Schmidt-Thieme,et al.  Near Real-time Geolocation Prediction in Twitter Streams via Matrix Factorization Based Regression , 2016, CIKM.

[9]  Deng Cai,et al.  What to Do Next: Modeling User Behaviors by Time-LSTM , 2017, IJCAI.

[10]  Yoshua Bengio,et al.  Show, Attend and Tell: Neural Image Caption Generation with Visual Attention , 2015, ICML.

[11]  Heng Tao Shen,et al.  Principal Component Analysis , 2009, Encyclopedia of Biometrics.

[12]  Sanjeev Arora,et al.  A Simple but Tough-to-Beat Baseline for Sentence Embeddings , 2017, ICLR.

[13]  Fuzhen Zhuang,et al.  Where to Go Next: A Spatio-Temporal Gated Network for Next POI Recommendation , 2019, AAAI.

[14]  Yoshua Bengio,et al.  End-to-end attention-based large vocabulary speech recognition , 2015, 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[15]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[16]  Jiawei Han,et al.  Mining periodic behaviors for moving objects , 2010, KDD.

[17]  Jeffrey Pennington,et al.  GloVe: Global Vectors for Word Representation , 2014, EMNLP.

[18]  Jian Dai,et al.  Personalized route recommendation using big trajectory data , 2015, 2015 IEEE 31st International Conference on Data Engineering.

[19]  Chao Zhang,et al.  SERM: A Recurrent Model for Next Location Prediction in Semantic Trajectories , 2017, CIKM.

[20]  Bruno Martins,et al.  Predicting future locations with hidden Markov models , 2012, UbiComp.

[21]  Jeffrey Dean,et al.  Efficient Estimation of Word Representations in Vector Space , 2013, ICLR.

[22]  Luming Zhang,et al.  GMove: Group-Level Mobility Modeling Using Geo-Tagged Social Media , 2016, KDD.

[23]  Christopher D. Manning,et al.  Effective Approaches to Attention-based Neural Machine Translation , 2015, EMNLP.

[24]  John R. Hershey,et al.  Attention-Based Multimodal Fusion for Video Description , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[25]  Yoshua Bengio,et al.  Describing Multimedia Content Using Attention-Based Encoder-Decoder Networks , 2015, IEEE Transactions on Multimedia.

[26]  Tieniu Tan,et al.  Predicting the Next Location: A Recurrent Model with Spatial and Temporal Contexts , 2016, AAAI.

[27]  Daqing Zhang,et al.  Urban Traffic Modelling and Prediction Using Large Scale Taxi GPS Traces , 2012, Pervasive.