Point-of-Interest Recommender Systems based on Location-Based Social Networks: A Survey from an Experimental Perspective

TL;DR

This survey reviews the last decade of point-of-interest recommendation systems based on location data from social networks, highlighting popular techniques, evaluation methods, and challenges like reproducibility issues.

Contribution

It provides a comprehensive categorization of algorithms and evaluation methodologies, and discusses open challenges and opportunities in LBSN-based POI recommendation research.

Findings

Deep learning approaches are frequently used in recent POI recommendation systems.

Geographical signals are a common information source exploited in algorithms.

Reproducibility issues hinder progress and real-world application.

Abstract

Point-of-Interest recommendation is an increasing research and developing area within the widely adopted technologies known as Recommender Systems. Among them, those that exploit information coming from Location-Based Social Networks (LBSNs) are very popular nowadays and could work with different information sources, which pose several challenges and research questions to the community as a whole. We present a systematic review focused on the research done in the last 10 years about this topic. We discuss and categorize the algorithms and evaluation methodologies used in these works and point out the opportunities and challenges that remain open in the field. More specifically, we report the leading recommendation techniques and information sources that have been exploited more often (such as the geographical signal and deep learning approaches) while we also alert about the lack of reproducibility in the field that may hinder real performance improvements.