SUCP

Leveraging Social Influence based on Users Activity Centers for Point-of-Interest Recommendation ()

Direct Friends (i.e., users who follow each other in an LBSN) and Distant Friends (i.e., users with commonly visited check-ins) usually have close opinions, even some friendships are made because of these behavioral similarities. Our analysis reveals the social behavior pattern of users for geographic activity centers. This paper proposes a new approach that examines user's preferences based on three contextual factors: geographical, social, and temporal information. we compare the performance of our SUCP with its variant, called SUCP-NoSocial.

you can read the paper for more details.

Environment Settings

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

To run the code

You need just run the recommendation.py then enter data-name and beta value, like this: ' gowalla 0.7 '

• To change the dataset, you have to write its name in the recommendation.py.
• Note that use 0.7 for the Gowalla beta and 0.8 for the Yelp betta, according to the paper.

Cite

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

This repository contains the implementation of Leveraging Social Influence based on Users Activity Centers for Point-of-Interest Recommendation presented in the IPM 2021 paper.

Contact

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