Multi-Context-Aware Location Recommendation Using Tensor Decomposition

Jing Lu,Martin A Indeche

doi:10.1109/access.2020.2983555

Abstract

With the rapid growth of information generated by online social network platforms and the increased usage of Location-Based Social Networks, location recommendation research has attracted more attention both in academic and industry. However, the problem of data sparsity still posses a severe challenge to the existing location recommendation methods. Moreover, extracting and modeling multiple contextual information, which is one of the key factors that influences user check-in preferences, is another big challenge faced by the existing methods. Many of the existing location recommendation methods have low accuracy because they utilize limited contextual information when modeling user check-in behaviors. In this paper, we propose a Multi-Context-aware Location Recommendation using Tensor Decomposition (MCLR-TD) approach that incorporates multiple context information at different granularity scales in modeling user check-in behavior. We use a four mode tensor to model the relationship among the four dimensions: users, locations, time and weather. In order to reduce the data sparsity problem, we further construct four feature matrices that are collaboratively decomposed with the tensor. We carry out extensive experiments on two real-world datasets collected from Foursquare and Yelp and the results demonstrate the effectiveness of our approach.

Highlights

With the huge amount of information available on the web, many people regularly face the problem of ‘‘choice paralysis’’
WORK In this paper, we proposed Multi-Context-aware Location Recommendation using Tensor Decomposition (MCLR-Tucker decomposition (TD)) approach that utilizes multiple contextual information of time and weather in making location recommendation using collaborative tensormatrix decomposition
We first carried out an extensive data analysis on the two datasets to determine how human checkin behaviors are affected by contextual factors

Summary

Introduction

With the huge amount of information available on the web, many people regularly face the problem of ‘‘choice paralysis’’. It is very hard for them to make a satisfying decision on which locations to visit from the huge number of Point of Interests (POIs). POI Recommendation Systems try to solve this problem by utilizing users’ historical check-in data available in Location Based Social Networks (LBSNs) and recommending POIs that users may be interested in. This is achieved by taking advantage of the increased usage of mobile devices that store and provide huge amount of users’ check-in information alongside LBSNs like Foursquare, Brightkite and Yelp. POI recommendation can help users to explore interesting but unvisited locations of a given region and enrich their experience.

Objectives

Methods

Findings

Conclusion