schliessen

Filtern

 

Bibliotheken

Augmented Collaborative Filtering for Sparseness Reduction in Personalized POI Recommendation

As mobile device penetration increases, it has become pervasive for images to be associated with locations in the form of geotags. Geotags bridge the gap between the physical world and the cyberspace, giving rise to new opportunities to extract further insights into user preferences and behaviors. I... Full description

Journal Title: ACM Transactions on Intelligent Systems and Technology (TIST) 27 September 2017, Vol.8(5), pp.1-23
Main Author: Cui, Chaoran
Other Authors: Shen, Jialie , Nie, Liqiang , Hong, Richang , Ma, Jun
Format: Electronic Article Electronic Article
Language: English
Subjects:
ID: E-ISSN: 2157-6912 ; DOI: 10.1145/3086635
Link: http://dl.acm.org/citation.cfm?id=3086635
Zum Text:
SendSend as email Add to Book BagAdd to Book Bag
Staff View
recordid: acm3086635
title: Augmented Collaborative Filtering for Sparseness Reduction in Personalized POI Recommendation
format: Article
creator:
  • Cui, Chaoran
  • Shen, Jialie
  • Nie, Liqiang
  • Hong, Richang
  • Ma, Jun
subjects:
  • Geotagged Photos
  • Hypergraph-Based Learning
  • Personalized Poi Recommendation
  • Engineering
  • Computer Science
ispartof: ACM Transactions on Intelligent Systems and Technology (TIST), 27 September 2017, Vol.8(5), pp.1-23
description: As mobile device penetration increases, it has become pervasive for images to be associated with locations in the form of geotags. Geotags bridge the gap between the physical world and the cyberspace, giving rise to new opportunities to extract further insights into user preferences and behaviors. In this article, we aim to exploit geotagged photos from online photo-sharing sites for the purpose of personalized Point-of-Interest (POI) recommendation. Owing to the fact that most users have only very limited travel experiences, data sparseness poses a formidable challenge to personalized POI recommendation. To alleviate data sparseness, we propose to augment current collaborative filtering algorithms along from multiple perspectives. Specifically, hybrid preference cues comprising user-uploaded and user-favored photos are harvested to study users' tastes. Moreover, heterogeneous high-order relationship information is jointly captured from user social networks and POI multimodal contents with hypergraph models. We also build upon the matrix factorization algorithm to integrate the disparate sources of preference and relationship information, and apply our approach to directly optimize user preference rankings. Extensive experiments on a large and publicly accessible dataset well verified the potential of our approach for addressing data sparseness and offering quality recommendations to users, especially for those who have only limited travel experiences.
language: eng
source:
identifier: E-ISSN: 2157-6912 ; DOI: 10.1145/3086635
fulltext: fulltext
issn:
  • 2157-6912
  • 21576912
url: Link


@attributes
ID1005896142
RANK0.07
NO1
SEARCH_ENGINEprimo_central_multiple_fe
SEARCH_ENGINE_TYPEPrimo Central Search Engine
LOCALfalse
PrimoNMBib
record
control
sourcerecordid3086635
sourceidacm
recordidTN_acm3086635
sourcesystemPC
dbid
0ABGDV
1ABQDU
2ACM
3ADL
4AIYWX
5ASPBG
6AVWKF
7BDXCO
8FEDTE
9GUFHI
10HGAVV
display
typearticle
titleAugmented Collaborative Filtering for Sparseness Reduction in Personalized POI Recommendation
creatorCui, Chaoran ; Shen, Jialie ; Nie, Liqiang ; Hong, Richang ; Ma, Jun
ispartofACM Transactions on Intelligent Systems and Technology (TIST), 27 September 2017, Vol.8(5), pp.1-23
identifierE-ISSN: 2157-6912 ; DOI: 10.1145/3086635
subjectGeotagged Photos ; Hypergraph-Based Learning ; Personalized Poi Recommendation ; Engineering ; Computer Science
descriptionAs mobile device penetration increases, it has become pervasive for images to be associated with locations in the form of geotags. Geotags bridge the gap between the physical world and the cyberspace, giving rise to new opportunities to extract further insights into user preferences and behaviors. In this article, we aim to exploit geotagged photos from online photo-sharing sites for the purpose of personalized Point-of-Interest (POI) recommendation. Owing to the fact that most users have only very limited travel experiences, data sparseness poses a formidable challenge to personalized POI recommendation. To alleviate data sparseness, we propose to augment current collaborative filtering algorithms along from multiple perspectives. Specifically, hybrid preference cues comprising user-uploaded and user-favored photos are harvested to study users' tastes. Moreover, heterogeneous high-order relationship information is jointly captured from user social networks and POI multimodal contents with hypergraph models. We also build upon the matrix factorization algorithm to integrate the disparate sources of preference and relationship information, and apply our approach to directly optimize user preference rankings. Extensive experiments on a large and publicly accessible dataset well verified the potential of our approach for addressing data sparseness and offering quality recommendations to users, especially for those who have only limited travel experiences.
languageeng
source
version2
lds50peer_reviewed
links
openurl$$Topenurl_article
openurlfulltext$$Topenurlfull_article
backlink$$Uhttp://dl.acm.org/citation.cfm?id=3086635$$EView_record_in_ACM
search
creatorcontrib
0Cui, Chaoran
1Shen, Jialie
2Nie, Liqiang
3Hong, Richang
4Ma, Jun
titleAugmented Collaborative Filtering for Sparseness Reduction in Personalized POI Recommendation
description

As mobile device penetration increases, it has become pervasive for images to be associated with locations in the form of geotags. Geotags bridge the gap between the physical world and the cyberspace, giving rise to new opportunities to extract further insights into user preferences and behaviors. In this article, we aim to exploit geotagged photos from online photo-sharing sites for the purpose of personalized Point-of-Interest (POI) recommendation. Owing to the fact that most users have only very limited travel experiences, data sparseness poses a formidable challenge to personalized POI recommendation. To alleviate data sparseness, we propose to augment current collaborative filtering algorithms along from multiple perspectives. Specifically, hybrid preference cues comprising user-uploaded and user-favored photos are harvested to study users' tastes. Moreover, heterogeneous high-order relationship information is jointly captured from user social networks and POI multimodal contents with hypergraph models. We also build upon the matrix factorization algorithm to integrate the disparate sources of preference and relationship information, and apply our approach to directly optimize user preference rankings. Extensive experiments on a large and publicly accessible dataset well verified the potential of our approach for addressing data sparseness and offering quality recommendations to users, especially for those who have only limited travel experiences.

subject
0Geotagged Photos
1Hypergraph-Based Learning
2Personalized Poi Recommendation
3Engineering
4Computer Science
general
0English
1ACM
210.1145/3086635
3BIBSAM:2015-2018 (ACM Digital Library)
4Jisc Collections:Digital Library:2017-2019 (ACM Digital Library)
5ACM Digital Library
6KESLI (ACM Digital Library)
7SHEDL- 2014 (ACM Digital Library)
8ACM Digital Library (Association for Computing Machinery)
sourceidacm
recordidacm3086635
issn
02157-6912
121576912
rsrctypearticle
creationdate2017
addtitleACM Transactions on Intelligent Systems and Technology (TIST)
searchscope
0acm_full
1acm5
2acm6
3acm1
4acm3
5acm4
scope
0acm_full
1acm5
2acm6
3acm1
4acm3
5acm4
lsr44$$EView_record_in_ACM
tmp01
0BIBSAM:2015-2018 (ACM Digital Library)
1Jisc Collections:Digital Library:2017-2019 (ACM Digital Library)
2ACM Digital Library (Association for Computing Machinery)
3KESLI (ACM Digital Library)
4SHEDL- 2014 (ACM Digital Library)
tmp02
0ABGDV
1ABQDU
2ACM
3ADL
4AIYWX
5ASPBG
6AVWKF
7BDXCO
8FEDTE
9GUFHI
10HGAVV
startdate20170927
enddate20170927
lsr40ACM Transactions on Intelligent Systems and Technology (TIST), 27 September 2017, Vol.8 (5), pp.1-23
doi10.1145/3086635
citationpf 1 pt 23 vol 8 issue 5
lsr30VSR-Enriched:[issn]
sort
titleAugmented Collaborative Filtering for Sparseness Reduction in Personalized POI Recommendation
authorCui, Chaoran ; Shen, Jialie ; Nie, Liqiang ; Hong, Richang ; Ma, Jun
creationdate20170927
lso0120170927
facets
frbrgroupid4551575074192555174
frbrtype5
newrecords20171108
languageeng
topic
0Geotagged Photos
1Hypergraph-Based Learning
2Personalized Poi Recommendation
3Engineering
4Computer Science
collection
0BIBSAM:2015-2018 (ACM Digital Library)
1Jisc Collections:Digital Library:2017-2019 (ACM Digital Library)
2ACM Digital Library
3KESLI (ACM Digital Library)
4SHEDL- 2014 (ACM Digital Library)
prefilterarticles
rsrctypearticles
creatorcontrib
0Cui, Chaoran
1Shen, Jialie
2Nie, Liqiang
3Hong, Richang
4Ma, Jun
jtitleACM Transactions on Intelligent Systems and Technology (TIST)
creationdate2017
toplevelpeer_reviewed
delivery
delcategoryRemote Search Resource
fulltextfulltext
addata
aulast
0Cui
1Shen
2Nie
3Hong
4Ma
aufirst
0Chaoran
1Jialie
2Liqiang
3Richang
4Jun
auinitC
auinit1C
au
0Cui, Chaoran
1Shen, Jialie
2Nie, Liqiang
3Hong, Richang
4Ma, Jun
atitleAugmented Collaborative Filtering for Sparseness Reduction in Personalized POI Recommendation
jtitleACM Transactions on Intelligent Systems and Technology (TIST)
risdate20170927
volume8
issue5
spage1
epage23
pages1-23
eissn2157-6912
formatjournal
genrearticle
ristypeJOUR
abstract

As mobile device penetration increases, it has become pervasive for images to be associated with locations in the form of geotags. Geotags bridge the gap between the physical world and the cyberspace, giving rise to new opportunities to extract further insights into user preferences and behaviors. In this article, we aim to exploit geotagged photos from online photo-sharing sites for the purpose of personalized Point-of-Interest (POI) recommendation. Owing to the fact that most users have only very limited travel experiences, data sparseness poses a formidable challenge to personalized POI recommendation. To alleviate data sparseness, we propose to augment current collaborative filtering algorithms along from multiple perspectives. Specifically, hybrid preference cues comprising user-uploaded and user-favored photos are harvested to study users' tastes. Moreover, heterogeneous high-order relationship information is jointly captured from user social networks and POI multimodal contents with hypergraph models. We also build upon the matrix factorization algorithm to integrate the disparate sources of preference and relationship information, and apply our approach to directly optimize user preference rankings. Extensive experiments on a large and publicly accessible dataset well verified the potential of our approach for addressing data sparseness and offering quality recommendations to users, especially for those who have only limited travel experiences.

pubACM
doi10.1145/3086635
issn21576904
date2017-09-27