Exploiting different users' interactions for profiles enrichment in recommender systems

Arthur F. Da Costa; Rafael D. Martins; Marcelo G. Manzato; Ricardo J.G.B. Campello

doi:10.1145/2851613.2851923

Exploiting different users' interactions for profiles enrichment in recommender systems

Arthur F. Da Costa, Rafael D. Martins, Marcelo G. Manzato, Ricardo J.G.B. Campello

University of São Paulo

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

Abstract

User profiling is an important aspect of recommender systems. It models users' preferences and is used to assess an item's relevance to a particular user. In this paper we propose a profiling approach which describes and enriches the users' preferences using multiple types of interactions. We show in our experiments that the enriched version of users' profiles is able to provide better recommendations.

Original language	English
Title of host publication	2016 Symposium on Applied Computing, SAC 2016
Publisher	Association for Computing Machinery
Publication date	4. Apr 2016
Pages	1080-1082
ISBN (Electronic)	9781450337397
DOIs	https://doi.org/10.1145/2851613.2851923
Publication status	Published - 4. Apr 2016
Externally published	Yes
Event	31st Annual ACM Symposium on Applied Computing, SAC 2016 - Pisa, Italy Duration: 4. Apr 2016 → 8. Apr 2016

Conference

Conference	31st Annual ACM Symposium on Applied Computing, SAC 2016
Country/Territory	Italy
City	Pisa
Period	04/04/2016 → 08/04/2016
Sponsor	ACM Special Interest Group on Applied Computing (SIGAPP)

Keywords

Multiple interactions
Recommender system
User profiling

Documents & Links

10.1145/2851613.2851923

SDU Link

Check access to the material in SDU Library's search engine

Cite this

@inproceedings{08a34b45ef7243d2847037b3bf9ed5dd,

title = "Exploiting different users' interactions for profiles enrichment in recommender systems",

abstract = "User profiling is an important aspect of recommender systems. It models users' preferences and is used to assess an item's relevance to a particular user. In this paper we propose a profiling approach which describes and enriches the users' preferences using multiple types of interactions. We show in our experiments that the enriched version of users' profiles is able to provide better recommendations.",

keywords = "Multiple interactions, Recommender system, User profiling",

author = "{Da Costa}, {Arthur F.} and Martins, {Rafael D.} and Manzato, {Marcelo G.} and Campello, {Ricardo J.G.B.}",

note = "Publisher Copyright: {\textcopyright} 2016 ACM.; 31st Annual ACM Symposium on Applied Computing, SAC 2016 ; Conference date: 04-04-2016 Through 08-04-2016",

year = "2016",

month = apr,

day = "4",

doi = "10.1145/2851613.2851923",

language = "English",

pages = "1080--1082",

booktitle = "2016 Symposium on Applied Computing, SAC 2016",

publisher = "Association for Computing Machinery",

address = "United States",

}

Da Costa, AF, Martins, RD, Manzato, MG & Campello, RJGB 2016, Exploiting different users' interactions for profiles enrichment in recommender systems. in 2016 Symposium on Applied Computing, SAC 2016. Association for Computing Machinery, pp. 1080-1082, 31st Annual ACM Symposium on Applied Computing, SAC 2016, Pisa, Italy, 04/04/2016. https://doi.org/10.1145/2851613.2851923

Exploiting different users' interactions for profiles enrichment in recommender systems. / Da Costa, Arthur F.; Martins, Rafael D.; Manzato, Marcelo G. et al.
2016 Symposium on Applied Computing, SAC 2016. Association for Computing Machinery, 2016. p. 1080-1082.

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

TY - GEN

T1 - Exploiting different users' interactions for profiles enrichment in recommender systems

AU - Da Costa, Arthur F.

AU - Martins, Rafael D.

AU - Manzato, Marcelo G.

AU - Campello, Ricardo J.G.B.

PY - 2016/4/4

Y1 - 2016/4/4

N2 - User profiling is an important aspect of recommender systems. It models users' preferences and is used to assess an item's relevance to a particular user. In this paper we propose a profiling approach which describes and enriches the users' preferences using multiple types of interactions. We show in our experiments that the enriched version of users' profiles is able to provide better recommendations.

AB - User profiling is an important aspect of recommender systems. It models users' preferences and is used to assess an item's relevance to a particular user. In this paper we propose a profiling approach which describes and enriches the users' preferences using multiple types of interactions. We show in our experiments that the enriched version of users' profiles is able to provide better recommendations.

KW - Multiple interactions

KW - Recommender system

KW - User profiling

UR - http://www.scopus.com/inward/record.url?scp=84975824249&partnerID=8YFLogxK

U2 - 10.1145/2851613.2851923

DO - 10.1145/2851613.2851923

M3 - Article in proceedings

AN - SCOPUS:84975824249

SP - 1080

EP - 1082

BT - 2016 Symposium on Applied Computing, SAC 2016

PB - Association for Computing Machinery

T2 - 31st Annual ACM Symposium on Applied Computing, SAC 2016

Y2 - 4 April 2016 through 8 April 2016

ER -

Exploiting different users' interactions for profiles enrichment in recommender systems

Abstract

Conference

Keywords

Documents & Links

SDU Link

Other files and links

Fingerprint

Cite this