Implementing Recommendations in the PATHS System

Paul Clough; Arantxa Otegi; Eneko Agirre; Mark M Hall

doi:10.1007/978-3-319-08425-1_17

Implementing Recommendations in the PATHS System

Paul Clough, Arantxa Otegi, Eneko Agirre, Mark M Hall

Computer Science

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

4 Citations (Scopus)

Abstract

In this paper we describe the design and implementation of non-personalized recommendations in the PATHS system. This system allows users to explore items from Europeana in new ways. Recommendations of the type “people who viewed this item also viewed this item” are powered by pairs of viewed items mined from Europeana. However, due to limited usage data only 10.3 % of items in the PATHS dataset have recommendations (4.3 % of item pairs visited more than once). Therefore, “related items”, a form of content-based recommendation, are offered to users based on identifying similar items. We discuss some of the problems with implementing recommendations and highlight areas for future work in the PATHS project.

Original language	English
Title of host publication	Theory and Practice of Digital Libraries -- TPDL 2013 Selected Workshops
Publisher	Springer International Publishing
Pages	169-173
Number of pages	5
Volume	416
ISBN (Print)	9783319084244
DOIs	https://doi.org/10.1007/978-3-319-08425-1_17
Publication status	Published - Aug 2014

Publication series

Name	Communications in Computer and Information Science
Volume	416 CCIS

Keywords

Digital libraries
Recommendations
Europeana

Access to Document

10.1007/978-3-319-08425-1_17

http://dx.doi.org/10.1007/978-3-319-08425-1_17

Cite this

@inbook{8ada73edd2044d0fb63767412544e54a,

title = "Implementing Recommendations in the PATHS System",

abstract = "In this paper we describe the design and implementation of non-personalized recommendations in the PATHS system. This system allows users to explore items from Europeana in new ways. Recommendations of the type “people who viewed this item also viewed this item” are powered by pairs of viewed items mined from Europeana. However, due to limited usage data only 10.3 % of items in the PATHS dataset have recommendations (4.3 % of item pairs visited more than once). Therefore, “related items”, a form of content-based recommendation, are offered to users based on identifying similar items. We discuss some of the problems with implementing recommendations and highlight areas for future work in the PATHS project.",

keywords = "Digital libraries, Recommendations, Europeana",

author = "Paul Clough and Arantxa Otegi and Eneko Agirre and Hall, {Mark M}",

year = "2014",

month = aug,

doi = "10.1007/978-3-319-08425-1_17",

language = "English",

isbn = "9783319084244",

volume = "416",

series = "Communications in Computer and Information Science",

publisher = "Springer International Publishing",

pages = "169--173",

booktitle = "Theory and Practice of Digital Libraries -- TPDL 2013 Selected Workshops",

}

Implementing Recommendations in the PATHS System. / Clough, Paul; Otegi, Arantxa; Agirre, Eneko et al.
Theory and Practice of Digital Libraries -- TPDL 2013 Selected Workshops. Vol. 416 Springer International Publishing, 2014. p. 169-173 (Communications in Computer and Information Science; Vol. 416 CCIS).

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

TY - CHAP

T1 - Implementing Recommendations in the PATHS System

AU - Clough, Paul

AU - Otegi, Arantxa

AU - Agirre, Eneko

AU - Hall, Mark M

PY - 2014/8

Y1 - 2014/8

N2 - In this paper we describe the design and implementation of non-personalized recommendations in the PATHS system. This system allows users to explore items from Europeana in new ways. Recommendations of the type “people who viewed this item also viewed this item” are powered by pairs of viewed items mined from Europeana. However, due to limited usage data only 10.3 % of items in the PATHS dataset have recommendations (4.3 % of item pairs visited more than once). Therefore, “related items”, a form of content-based recommendation, are offered to users based on identifying similar items. We discuss some of the problems with implementing recommendations and highlight areas for future work in the PATHS project.

AB - In this paper we describe the design and implementation of non-personalized recommendations in the PATHS system. This system allows users to explore items from Europeana in new ways. Recommendations of the type “people who viewed this item also viewed this item” are powered by pairs of viewed items mined from Europeana. However, due to limited usage data only 10.3 % of items in the PATHS dataset have recommendations (4.3 % of item pairs visited more than once). Therefore, “related items”, a form of content-based recommendation, are offered to users based on identifying similar items. We discuss some of the problems with implementing recommendations and highlight areas for future work in the PATHS project.

KW - Digital libraries

KW - Recommendations

KW - Europeana

UR - http://www.mendeley.com/research/implementing-recommendations-paths-system

U2 - 10.1007/978-3-319-08425-1_17

DO - 10.1007/978-3-319-08425-1_17

M3 - Chapter

SN - 9783319084244

VL - 416

T3 - Communications in Computer and Information Science

SP - 169

EP - 173

BT - Theory and Practice of Digital Libraries -- TPDL 2013 Selected Workshops

PB - Springer International Publishing

ER -

Implementing Recommendations in the PATHS System

Abstract

Publication series

Keywords

Access to Document

Other files and links

Fingerprint

Cite this