Bringing Diversity to Recommendation Lists - An Analysis of the
Placement of Diverse Items

D 2013

Bringing Diversity to Recommendation Lists - An Analysis of the Placement of Diverse Items

GE, Mouzhi; Dietmar JANNACH and Fatih GEDIKLI

Basic information

Original name

Bringing Diversity to Recommendation Lists - An Analysis of the Placement of Diverse Items

Authors

GE, Mouzhi; Dietmar JANNACH and Fatih GEDIKLI

Edition

BERLIN, ENTERPRISE INFORMATION SYSTEMS, ICEIS 2012, p. 293-305, 13 pp. 2013

Publisher

SPRINGER-VERLAG BERLIN

Other information

Language

English

Type of outcome

Proceedings paper

Field of Study

10201 Computer sciences, information science, bioinformatics

Confidentiality degree

is not subject to a state or trade secret

Organization unit

Faculty of Informatics

ISSN

DOI

http://dx.doi.org/10.1007/978-3-642-40654-6_18

UT WoS

000333200500018

Keywords in English

Recommender system; Evaluation; Diversity; Serendipity; Item ranking; User satisfaction

Changed: 2/4/2017 16:43, doc. Mouzhi Ge, Ph.D.

Abstract

In the original language

The core task of a recommender system is to provide users with a ranked list of recommended items. In many cases, the ranking is based one a recommendation score representing the estimated degree to which the users will like them. Up to now research specifically focused on the accuracy of recommender algorithms in predicting the relevance of items for a given user. However, researchers agree that there are other factors than prediction accuracy which can have a significant effect on the overall quality of a recommender system. Therefore, additional and complementary metrics, including diversity, novelty, transparency and serendipity should be used to evaluate the quality of recommender systems. In this paper we will focus on diversity which has been more widely discussed in recent research and is often considered to be a factor which is equally important as accuracy. In particular we address the question of how to place diverse items in a recommendation list and measure the user-perceived level of diversity. Differently placing the diverse items can affect perceived diversity and the level of serendipity. Furthermore, the results of our analysis show that including diverse items in a recommendation list can both increase and sometimes even decrease the perceived diversity and that the effect depends on how the diverse items are arranged.

Cite

GE, Mouzhi; Dietmar JANNACH and Fatih GEDIKLI. Bringing Diversity to Recommendation Lists - An Analysis of the Placement of Diverse Items. In Cordeiro, J Maciaszek, LA Filipe, J. ENTERPRISE INFORMATION SYSTEMS, ICEIS 2012. BERLIN: SPRINGER-VERLAG BERLIN, 2013, p. 293-305. ISSN 1865-1348. Available from: https://dx.doi.org/10.1007/978-3-642-40654-6_18.

@inproceedings{1377072,
   author = {Ge, Mouzhi and Jannach, Dietmar and Gedikli, Fatih},
   address = {BERLIN},
   booktitle = {ENTERPRISE INFORMATION SYSTEMS, ICEIS 2012},
   doi = {http://dx.doi.org/10.1007/978-3-642-40654-6_18},
   editor = {Cordeiro, J Maciaszek, LA Filipe, J},
   keywords = {Recommender system; Evaluation; Diversity; Serendipity; Item ranking; User satisfaction},
   language = {eng},
   location = {BERLIN},
   pages = {293-305},
   publisher = {SPRINGER-VERLAG BERLIN},
   title = {Bringing Diversity to Recommendation Lists - An Analysis of the Placement of Diverse Items},
   year = {2013}
}

TY  - CONF
ID  - 1377072
AU  - Ge, Mouzhi - Jannach, Dietmar - Gedikli, Fatih
PY  - 2013
TI  - Bringing Diversity to Recommendation Lists - An Analysis of the Placement of Diverse Items
PB  - SPRINGER-VERLAG BERLIN
CY  - BERLIN
KW  - Recommender system
KW  - Evaluation
KW  - Diversity
KW  - Serendipity
KW  - Item ranking
KW  - User satisfaction
N2  - The core task of a recommender system is to provide users with a ranked list of recommended items. In many cases, the ranking is based one a recommendation score representing the estimated degree to which the users will like them. Up to now research specifically focused on the accuracy of recommender algorithms in predicting the relevance of items for a given user. However, researchers agree that there are other factors than prediction accuracy which can have a significant effect on the overall quality of a recommender system. Therefore, additional and complementary metrics, including diversity, novelty, transparency and serendipity should be used to evaluate the quality of recommender systems. In this paper we will focus on diversity which has been more widely discussed in recent research and is often considered to be a factor which is equally important as accuracy. In particular we address the question of how to place diverse items in a recommendation list and measure the user-perceived level of diversity. Differently placing the diverse items can affect perceived diversity and the level of serendipity. Furthermore, the results of our analysis show that including diverse items in a recommendation list can both increase and sometimes even decrease the perceived diversity and that the effect depends on how the diverse items are arranged.
ER  -

GE, Mouzhi; Dietmar JANNACH and Fatih GEDIKLI. Bringing Diversity to Recommendation Lists - An Analysis of the Placement of Diverse Items. In Cordeiro, J Maciaszek, LA Filipe, J. \textit{ENTERPRISE INFORMATION SYSTEMS, ICEIS 2012}. BERLIN: SPRINGER-VERLAG BERLIN, 2013, p.~293-305. ISSN~1865-1348. Available from: https://dx.doi.org/10.1007/978-3-642-40654-6\_{}18.

Přehled o publikaci