Geographic diversification of recommended POIs in frequently visited areas

H. A.N. Jungkyu, Hayato Yamana

Research output: Contribution to journalArticle

Abstract

In the personalized Point-Of-Interest (POI) (or venue) recommendation, the diversity of recommended POIs is an important aspect. Diversity is especially important when POIs are recommended in the target users' frequently visited areas, because users are likely to revisit such areas. In addition to the (POI) category diversity that is a popular diversification objective in recommendation domains, diversification of recommended POI locations is an interesting subject itself. Despite its importance, existing POI recommender studies generally focus on and evaluate prediction accuracy. In this article, geographical diversification (geo-diversification), a novel diversification concept that aims to increase recommendation coverage for a target users' geographic areas of interest, is introduced, from which a method that improves geo-diversity as an addition to existing state-of-the-art POI recommenders is proposed. In experiments with the datasets from two real Location Based Social Networks (LSBNs), we first analyze the performance of four state-of-the-art POI recommenders from various evaluation perspectives including category diversity and geo-diversity that have not been examined previously. The proposed method consistently improves geo-diversity (CPR(geo)@20) by 5 to 12% when combined with four state-of-the-art POI recommenders with negligible prediction accuracy (Recall@20) loss and provides 6 to 18% geo-diversity improvement with tolerable prediction accuracy loss (up to 2.4%).

Original languageEnglish
Article number1
JournalACM Transactions on Information Systems
Volume38
Issue number1
DOIs
Publication statusPublished - 2019 Oct

Fingerprint

Geographic diversification
Experiments
Prediction accuracy
Diversification
Evaluation
Geographical diversification
Social networks
Experiment

Keywords

  • Diversity
  • Geographical diversity
  • LBSN
  • POI
  • POI recommendation
  • Recommendation

ASJC Scopus subject areas

  • Information Systems
  • Business, Management and Accounting(all)
  • Computer Science Applications

Cite this

Geographic diversification of recommended POIs in frequently visited areas. / Jungkyu, H. A.N.; Yamana, Hayato.

In: ACM Transactions on Information Systems, Vol. 38, No. 1, 1, 10.2019.

Research output: Contribution to journalArticle

@article{1954fc919f754384acaeaf4d589ec2b4,
title = "Geographic diversification of recommended POIs in frequently visited areas",
abstract = "In the personalized Point-Of-Interest (POI) (or venue) recommendation, the diversity of recommended POIs is an important aspect. Diversity is especially important when POIs are recommended in the target users' frequently visited areas, because users are likely to revisit such areas. In addition to the (POI) category diversity that is a popular diversification objective in recommendation domains, diversification of recommended POI locations is an interesting subject itself. Despite its importance, existing POI recommender studies generally focus on and evaluate prediction accuracy. In this article, geographical diversification (geo-diversification), a novel diversification concept that aims to increase recommendation coverage for a target users' geographic areas of interest, is introduced, from which a method that improves geo-diversity as an addition to existing state-of-the-art POI recommenders is proposed. In experiments with the datasets from two real Location Based Social Networks (LSBNs), we first analyze the performance of four state-of-the-art POI recommenders from various evaluation perspectives including category diversity and geo-diversity that have not been examined previously. The proposed method consistently improves geo-diversity (CPR(geo)@20) by 5 to 12{\%} when combined with four state-of-the-art POI recommenders with negligible prediction accuracy (Recall@20) loss and provides 6 to 18{\%} geo-diversity improvement with tolerable prediction accuracy loss (up to 2.4{\%}).",
keywords = "Diversity, Geographical diversity, LBSN, POI, POI recommendation, Recommendation",
author = "Jungkyu, {H. A.N.} and Hayato Yamana",
year = "2019",
month = "10",
doi = "10.1145/3362505",
language = "English",
volume = "38",
journal = "ACM Transactions on Information Systems",
issn = "1046-8188",
publisher = "Association for Computing Machinery (ACM)",
number = "1",

}

TY - JOUR

T1 - Geographic diversification of recommended POIs in frequently visited areas

AU - Jungkyu, H. A.N.

AU - Yamana, Hayato

PY - 2019/10

Y1 - 2019/10

N2 - In the personalized Point-Of-Interest (POI) (or venue) recommendation, the diversity of recommended POIs is an important aspect. Diversity is especially important when POIs are recommended in the target users' frequently visited areas, because users are likely to revisit such areas. In addition to the (POI) category diversity that is a popular diversification objective in recommendation domains, diversification of recommended POI locations is an interesting subject itself. Despite its importance, existing POI recommender studies generally focus on and evaluate prediction accuracy. In this article, geographical diversification (geo-diversification), a novel diversification concept that aims to increase recommendation coverage for a target users' geographic areas of interest, is introduced, from which a method that improves geo-diversity as an addition to existing state-of-the-art POI recommenders is proposed. In experiments with the datasets from two real Location Based Social Networks (LSBNs), we first analyze the performance of four state-of-the-art POI recommenders from various evaluation perspectives including category diversity and geo-diversity that have not been examined previously. The proposed method consistently improves geo-diversity (CPR(geo)@20) by 5 to 12% when combined with four state-of-the-art POI recommenders with negligible prediction accuracy (Recall@20) loss and provides 6 to 18% geo-diversity improvement with tolerable prediction accuracy loss (up to 2.4%).

AB - In the personalized Point-Of-Interest (POI) (or venue) recommendation, the diversity of recommended POIs is an important aspect. Diversity is especially important when POIs are recommended in the target users' frequently visited areas, because users are likely to revisit such areas. In addition to the (POI) category diversity that is a popular diversification objective in recommendation domains, diversification of recommended POI locations is an interesting subject itself. Despite its importance, existing POI recommender studies generally focus on and evaluate prediction accuracy. In this article, geographical diversification (geo-diversification), a novel diversification concept that aims to increase recommendation coverage for a target users' geographic areas of interest, is introduced, from which a method that improves geo-diversity as an addition to existing state-of-the-art POI recommenders is proposed. In experiments with the datasets from two real Location Based Social Networks (LSBNs), we first analyze the performance of four state-of-the-art POI recommenders from various evaluation perspectives including category diversity and geo-diversity that have not been examined previously. The proposed method consistently improves geo-diversity (CPR(geo)@20) by 5 to 12% when combined with four state-of-the-art POI recommenders with negligible prediction accuracy (Recall@20) loss and provides 6 to 18% geo-diversity improvement with tolerable prediction accuracy loss (up to 2.4%).

KW - Diversity

KW - Geographical diversity

KW - LBSN

KW - POI

KW - POI recommendation

KW - Recommendation

UR - http://www.scopus.com/inward/record.url?scp=85074170101&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85074170101&partnerID=8YFLogxK

U2 - 10.1145/3362505

DO - 10.1145/3362505

M3 - Article

AN - SCOPUS:85074170101

VL - 38

JO - ACM Transactions on Information Systems

JF - ACM Transactions on Information Systems

SN - 1046-8188

IS - 1

M1 - 1

ER -