rahmanidashti/stacp

Joint Geographical and Temporal Modeling based on Matrix Factorization for Point-of-Interest Recommendation - ECIR 2020

STACP

Joint Geographical and Temporal Modeling based on Matrix Factorization for Point-of-Interest Recommendation (ECIR 2020)

Environment Settings

• Python version: '2.7'
• You have to install the required libraries

To run the code

You need just run the recommendation.py

The TimeAwareMF.py lib is implemented in Python 2. Therefore you should run the model with Python 2.

• To change the dataset, you have to write its name in the recommendation.py.

Cite

Please cite our paper if you use our datasets or implementations:

@inproceedings{rahmani2020joint,
  title={Joint geographical and temporal modeling based on matrix factorization for point-of-interest recommendation},
  author={Rahmani, Hossein A and Aliannejadi, Mohammad and Baratchi, Mitra and Crestani, Fabio},
  booktitle={European Conference on Information Retrieval},
  pages={205--219},
  year={2020},
  organization={Springer}
}

This repository contains the implementation of the Joint geographical and temporal modeling based on matrix factorization for point-of-interest recommendation presented in the ECIR 2020 paper. More details will be updated later.

Acknowledge

For implemenation we got some information and inspiration of the codes that provided by the following paper:

Liu, Yiding, et al. "An experimental evaluation of point-of-interest recommendation in location-based social networks." in VLDB, 2017

Contact

If you have any questions, do not hesitate to contact us by [email protected] or [email protected], we will be happy to assist.

stacp's Issues

Thesis experiment question

./tmp/sigma.npy Error

I am getting the following error in TimeAwareMF.py. Do I need to /tmp.sigma.npy? Do you know how can we solve this issue?

Thank you!

line 77, in train
np.save("./tmp/sigma", sigma)

IOError: [Errno 2] No such file or directory: './tmp/sigma.npy'

Thesis experiment question

For the STACP code I ran, the average precision of all users(Precision@10) calculated using the Gowalla dataset is only 0.021179. Do I need to change the source code to reach 0.0383 precision?

# Dataset Format

I'm very interested in your research work，and thank you for publishing the code. But I am confused about the Foursquare_train.txt file format? What does the first, second and third columns stand for, respectively. I'm looking forward to your reply