Real-time event embedding for POI recommendation

Pei Yi Hao, Weng Hang Cheang, Jung-Hsien Chiang

Research output: Contribution to journalArticle

Abstract

Location-based social networks (LBSNs) allow users to check-in and share daily lives with others. We have witnessed very rapid development of LBSNs in recent years. Point-of-Interest (POI) recommendation is one of the core services in LBSNs. In this study, we propose a real-time POI embedding model. Instead of capturing intrinsic information, the proposed approach is able to mine real-time information of places and learn the latent representations according to the corresponding geo-tagged posts. On one hand, we employ a Convolutional Neural Networks (CNN) to mine textual information of POIs and learn their intrinsic representation. On the other hand, a multimodal embedding model of location, time and text is applied to keep monitoring posts on POIs and extracts a set of features for representing events or burst information that may attract users. Furthermore, we combine real-time POI embedding with matrix factorization method and propose a more comprehensive POI recommendation algorithm. To verify the effectiveness of our proposed method, we conduct experiments on Twitter dataset with geo-tagged tweets in NYC. Experimental results show that POI recommendation system with taking real-time event into consideration can strongly improve the performance than the one without.

Original languageEnglish
Pages (from-to)1-11
Number of pages11
JournalNeurocomputing
Volume349
DOIs
Publication statusPublished - 2019 Jul 15

Fingerprint

Social Support
Recommender systems
Factorization
Neural networks
Monitoring
Experiments
Datasets

All Science Journal Classification (ASJC) codes

  • Computer Science Applications
  • Cognitive Neuroscience
  • Artificial Intelligence

Cite this

Hao, Pei Yi ; Cheang, Weng Hang ; Chiang, Jung-Hsien. / Real-time event embedding for POI recommendation. In: Neurocomputing. 2019 ; Vol. 349. pp. 1-11.
@article{abbc509722c644e5a9cde48d92370fbb,
title = "Real-time event embedding for POI recommendation",
abstract = "Location-based social networks (LBSNs) allow users to check-in and share daily lives with others. We have witnessed very rapid development of LBSNs in recent years. Point-of-Interest (POI) recommendation is one of the core services in LBSNs. In this study, we propose a real-time POI embedding model. Instead of capturing intrinsic information, the proposed approach is able to mine real-time information of places and learn the latent representations according to the corresponding geo-tagged posts. On one hand, we employ a Convolutional Neural Networks (CNN) to mine textual information of POIs and learn their intrinsic representation. On the other hand, a multimodal embedding model of location, time and text is applied to keep monitoring posts on POIs and extracts a set of features for representing events or burst information that may attract users. Furthermore, we combine real-time POI embedding with matrix factorization method and propose a more comprehensive POI recommendation algorithm. To verify the effectiveness of our proposed method, we conduct experiments on Twitter dataset with geo-tagged tweets in NYC. Experimental results show that POI recommendation system with taking real-time event into consideration can strongly improve the performance than the one without.",
author = "Hao, {Pei Yi} and Cheang, {Weng Hang} and Jung-Hsien Chiang",
year = "2019",
month = "7",
day = "15",
doi = "10.1016/j.neucom.2019.04.022",
language = "English",
volume = "349",
pages = "1--11",
journal = "Neurocomputing",
issn = "0925-2312",
publisher = "Elsevier",

}

Real-time event embedding for POI recommendation. / Hao, Pei Yi; Cheang, Weng Hang; Chiang, Jung-Hsien.

In: Neurocomputing, Vol. 349, 15.07.2019, p. 1-11.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Real-time event embedding for POI recommendation

AU - Hao, Pei Yi

AU - Cheang, Weng Hang

AU - Chiang, Jung-Hsien

PY - 2019/7/15

Y1 - 2019/7/15

N2 - Location-based social networks (LBSNs) allow users to check-in and share daily lives with others. We have witnessed very rapid development of LBSNs in recent years. Point-of-Interest (POI) recommendation is one of the core services in LBSNs. In this study, we propose a real-time POI embedding model. Instead of capturing intrinsic information, the proposed approach is able to mine real-time information of places and learn the latent representations according to the corresponding geo-tagged posts. On one hand, we employ a Convolutional Neural Networks (CNN) to mine textual information of POIs and learn their intrinsic representation. On the other hand, a multimodal embedding model of location, time and text is applied to keep monitoring posts on POIs and extracts a set of features for representing events or burst information that may attract users. Furthermore, we combine real-time POI embedding with matrix factorization method and propose a more comprehensive POI recommendation algorithm. To verify the effectiveness of our proposed method, we conduct experiments on Twitter dataset with geo-tagged tweets in NYC. Experimental results show that POI recommendation system with taking real-time event into consideration can strongly improve the performance than the one without.

AB - Location-based social networks (LBSNs) allow users to check-in and share daily lives with others. We have witnessed very rapid development of LBSNs in recent years. Point-of-Interest (POI) recommendation is one of the core services in LBSNs. In this study, we propose a real-time POI embedding model. Instead of capturing intrinsic information, the proposed approach is able to mine real-time information of places and learn the latent representations according to the corresponding geo-tagged posts. On one hand, we employ a Convolutional Neural Networks (CNN) to mine textual information of POIs and learn their intrinsic representation. On the other hand, a multimodal embedding model of location, time and text is applied to keep monitoring posts on POIs and extracts a set of features for representing events or burst information that may attract users. Furthermore, we combine real-time POI embedding with matrix factorization method and propose a more comprehensive POI recommendation algorithm. To verify the effectiveness of our proposed method, we conduct experiments on Twitter dataset with geo-tagged tweets in NYC. Experimental results show that POI recommendation system with taking real-time event into consideration can strongly improve the performance than the one without.

UR - http://www.scopus.com/inward/record.url?scp=85064397284&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85064397284&partnerID=8YFLogxK

U2 - 10.1016/j.neucom.2019.04.022

DO - 10.1016/j.neucom.2019.04.022

M3 - Article

AN - SCOPUS:85064397284

VL - 349

SP - 1

EP - 11

JO - Neurocomputing

JF - Neurocomputing

SN - 0925-2312

ER -