Point-of-Interest Recommendation in Location-Based Social Networks | springerprofessional.de

Springer Professional

Top

2018 | Book

Read chapter Read first chapter

Point-of-Interest Recommendation in Location-Based Social Networks

Authors: Shenglin Zhao, Prof. Michael R. Lyu, Prof. Irwin King

Publisher: Springer Singapore

Book Series : SpringerBriefs in Computer Science

Part of: Springer Professional "Wirtschaft+Technik" , Springer Professional "Technik" , Springer Professional "Wirtschaft"

Login to get access

About this book

This book systematically introduces Point-of-interest (POI) recommendations in Location-based Social Networks (LBSNs). Starting with a review of the advances in this area, the book then analyzes user mobility in LBSNs from geographical and temporal perspectives. Further, it demonstrates how to build a state-of-the-art POI recommendation system by incorporating the user behavior analysis. Lastly, the book discusses future research directions in this area.

This book is intended for professionals involved in POI recommendation and graduate students working on problems related to location-based services. It is assumed that readers have a basic knowledge of mathematics, as well as some background in recommendation systems.

Advertisement

Table of Contents

Frontmatter

Chapter 1. Introduction

Abstract

This chapter provides an overview of POI recommendation in LBSNs, including backgrounds, related work, and organizations of this book.

Shenglin Zhao, Michael R. Lyu, Irwin King

Chapter 2. Understanding Human Mobility from Geographical Perspective

Abstract

POI recommendation is a significant service for LBSNs. It recommends new places such as clubs, restaurants, and coffee bars to users. Whether recommended locations meet users’ interests depends on three factors: user preference, social influence, and geographical influence. Especially, capturing the geographical influence plays the most important role for POI recommendations. Previous studies observe that checked-in locations disperse around several centers and employ Gaussian distribution based models to approximate users’ check-in behaviors. Yet centers discovering methods are not satisfactory in prior work. This chapter shows how to exploit Gaussian mixture model (GMM) and genetic algorithm based Gaussian mixture model (GA-GMM) to capture geographical influence. Experimental results on a real-world LBSN dataset show that GMM beats several popular geographical capturing models in terms of POI recommendation, while GA-GMM excludes the effect of outliers and enhances GMM.

Shenglin Zhao, Michael R. Lyu, Irwin King

Chapter 3. Understanding Human Mobility from Temporal Perspective

Abstract

Understanding user mobility from the temporal perspective is the key to POI recommendation that mines user check-in sequences to suggest interesting locations for users. Because user mobility in LBSNs exhibits strong temporal patterns—for instance, users would like to check-in at restaurants at noon and visit bars at night. Hence, capturing the temporal influence is necessary to ensure the high performance in a POI recommendation system. This chapter summarizes the temporal characteristics of user mobility in LBSNs in three aspects: periodicity, consecutiveness, and non-uniformness. Moreover, an Aggregated Temporal Tensor Factorization (ATTF) model for POI recommendation is proposed to capture the three temporal features. Experiments on two real-world datasets show that the ATTF model achieves better performance than the state-of-the-art temporal models for POI recommendation.

Shenglin Zhao, Michael R. Lyu, Irwin King

Chapter 4. Geo-Teaser: Geo-Temporal Sequential Embedding Rank for POI Recommendation

Abstract

This chapter proposes a Geo-Temporal sequential embedding rank (Geo-Teaser) model for POI recommendation. Inspired by the success of the word2vec framework to model the sequential contexts, a temporal POI embedding model is proposed to learn POI representations under some particular temporal state. The temporal POI embedding model captures the contextual check-in information in sequences and the various temporal characteristics on different days as well. Furthermore, a new way of incorporating the geographical influence into the pairwise preference ranking method through discriminating the unvisited POIs according to geographical information, is employed to develop a geographically hierarchical pairwise preference ranking model. Finally, a unified framework is proposed to recommend POIs combining these two models. Experimental results on two real-life datasets show that the Geo-Teaser model outperforms state-of-the-art models.

Shenglin Zhao, Michael R. Lyu, Irwin King

Chapter 5. STELLAR: Spatial-Temporal Latent Ranking Model for Successive POI Recommendation

Abstract

Successive POI recommendation in LBSNs becomes a significant task since it helps users to navigate a large number of candidate POIs and provide the best POI recommendations based on users’ most recent check-in knowledge. However, all existing methods for successive POI recommendation only focus on modeling the correlation between POIs based on users’ check-in sequences, but ignore an important fact that successive POI recommendation is a time-subtle recommendation task. In fact, even with the same previous check-in information, users would prefer different successive POIs at different time. To capture the impact of time on successive POI recommendation, this chapter proposes a spatial-temporal latent ranking (STELLAR) method to explicitly model the interactions among user, POI, and time. In particular, the proposed STELLAR model is built upon a ranking-based pairwise tensor factorization framework with a fine-grained modeling of user-POI, POI-time, and POI-POI interactions for successive POI recommendation. Evaluations on two real-world datasets demonstrate that the STELLAR model outperforms state-of-the-art successive POI recommendation model about 20% in Precision@5 and Recall@5.

Shenglin Zhao, Michael R. Lyu, Irwin King

Chapter 6. Conclusion and Future Work

Abstract

This chapter summarizes the main contributions of this monograph and provides several interesting future directions.

Shenglin Zhao, Michael R. Lyu, Irwin King

Backmatter

Title: Point-of-Interest Recommendation in Location-Based Social Networks
Authors: Shenglin Zhao
Prof. Michael R. Lyu
Prof. Irwin King
Copyright Year: 2018
Publisher: Springer Singapore
Electronic ISBN: 978-981-13-1349-3
Print ISBN: 978-981-13-1348-6
DOI: https://doi.org/10.1007/978-981-13-1349-3

Premium Partner