A User-Centric Diversity by Design Recommender System for the Movie Application Domain

Research output: Contribution to book/anthology/report/conference proceedingArticle in proceedingResearchpeer-review

116 Downloads (Pure)

Abstract

Recommender systems (RS) have seen widespread adoption across the Internet. However, by emphasizing personalization through the optimization of accuracy-focused metrics, over-personalization may emerge, with negative effects on the user experience. A countermeasure to the problem is to diversify recommendations. In this paper, we present a solution that addresses the problem in the context of a movie application domain. The solution enhances diversity on four related dimensions, namely global coverage, local coverage, novelty, and redundancy. The proposed solution is designed to diversify users profiles, modeled on categorical preferences, within the same group in the recommendation filtering. We evaluate our approach on the Movielens dataset and show that our algorithm yields better results compared to random selection distant neighbors and performs comparably to one of the current state of the art solutions.
Original languageEnglish
Title of host publicationWWW '18 Companion Proceedings of the The Web Conference 2018
Number of pages9
PublisherAssociation for Computing Machinery
Publication date23 Apr 2018
Pages1381-1389
ISBN (Electronic)978-1-4503-5640-4
DOIs
Publication statusPublished - 23 Apr 2018
EventThe Web Conference 2018 - Workshop on Online Recommender Systems and User Modeling: continuous learning from web data - Lyon, France
Duration: 23 Apr 201827 Apr 2018
https://www2018.thewebconf.org

Conference

ConferenceThe Web Conference 2018 - Workshop on Online Recommender Systems and User Modeling: continuous learning from web data
LocationLyon
CountryFrance
Period23/04/201827/04/2018
Internet address

Fingerprint

Recommender systems
Redundancy
Internet

Keywords

  • diversity
  • Recommender System
  • movie recommendation
  • user clustering
  • diversification

Cite this

Zanitti, M., Kosta, S., & Sørensen, J. K. (2018). A User-Centric Diversity by Design Recommender System for the Movie Application Domain. In WWW '18 Companion Proceedings of the The Web Conference 2018 (pp. 1381-1389). Association for Computing Machinery. https://doi.org/10.1145/3184558.3191580
Zanitti, Michele ; Kosta, Sokol ; Sørensen, Jannick Kirk. / A User-Centric Diversity by Design Recommender System for the Movie Application Domain. WWW '18 Companion Proceedings of the The Web Conference 2018. Association for Computing Machinery, 2018. pp. 1381-1389
@inproceedings{c3585eff90214f0dab23312853d69569,
title = "A User-Centric Diversity by Design Recommender System for the Movie Application Domain",
abstract = "Recommender systems (RS) have seen widespread adoption across the Internet. However, by emphasizing personalization through the optimization of accuracy-focused metrics, over-personalization may emerge, with negative effects on the user experience. A countermeasure to the problem is to diversify recommendations. In this paper, we present a solution that addresses the problem in the context of a movie application domain. The solution enhances diversity on four related dimensions, namely global coverage, local coverage, novelty, and redundancy. The proposed solution is designed to diversify users profiles, modeled on categorical preferences, within the same group in the recommendation filtering. We evaluate our approach on the Movielens dataset and show that our algorithm yields better results compared to random selection distant neighbors and performs comparably to one of the current state of the art solutions.",
keywords = "diversity, recommender system, diversity, Recommender System, movie recommendation, user clustering, diversification",
author = "Michele Zanitti and Sokol Kosta and S{\o}rensen, {Jannick Kirk}",
year = "2018",
month = "4",
day = "23",
doi = "10.1145/3184558.3191580",
language = "English",
pages = "1381--1389",
booktitle = "WWW '18 Companion Proceedings of the The Web Conference 2018",
publisher = "Association for Computing Machinery",
address = "United States",

}

Zanitti, M, Kosta, S & Sørensen, JK 2018, A User-Centric Diversity by Design Recommender System for the Movie Application Domain. in WWW '18 Companion Proceedings of the The Web Conference 2018. Association for Computing Machinery, pp. 1381-1389, The Web Conference 2018 - Workshop on Online Recommender Systems and User Modeling: continuous learning from web data, France, 23/04/2018. https://doi.org/10.1145/3184558.3191580

A User-Centric Diversity by Design Recommender System for the Movie Application Domain. / Zanitti, Michele; Kosta, Sokol; Sørensen, Jannick Kirk.

WWW '18 Companion Proceedings of the The Web Conference 2018. Association for Computing Machinery, 2018. p. 1381-1389.

Research output: Contribution to book/anthology/report/conference proceedingArticle in proceedingResearchpeer-review

TY - GEN

T1 - A User-Centric Diversity by Design Recommender System for the Movie Application Domain

AU - Zanitti, Michele

AU - Kosta, Sokol

AU - Sørensen, Jannick Kirk

PY - 2018/4/23

Y1 - 2018/4/23

N2 - Recommender systems (RS) have seen widespread adoption across the Internet. However, by emphasizing personalization through the optimization of accuracy-focused metrics, over-personalization may emerge, with negative effects on the user experience. A countermeasure to the problem is to diversify recommendations. In this paper, we present a solution that addresses the problem in the context of a movie application domain. The solution enhances diversity on four related dimensions, namely global coverage, local coverage, novelty, and redundancy. The proposed solution is designed to diversify users profiles, modeled on categorical preferences, within the same group in the recommendation filtering. We evaluate our approach on the Movielens dataset and show that our algorithm yields better results compared to random selection distant neighbors and performs comparably to one of the current state of the art solutions.

AB - Recommender systems (RS) have seen widespread adoption across the Internet. However, by emphasizing personalization through the optimization of accuracy-focused metrics, over-personalization may emerge, with negative effects on the user experience. A countermeasure to the problem is to diversify recommendations. In this paper, we present a solution that addresses the problem in the context of a movie application domain. The solution enhances diversity on four related dimensions, namely global coverage, local coverage, novelty, and redundancy. The proposed solution is designed to diversify users profiles, modeled on categorical preferences, within the same group in the recommendation filtering. We evaluate our approach on the Movielens dataset and show that our algorithm yields better results compared to random selection distant neighbors and performs comparably to one of the current state of the art solutions.

KW - diversity

KW - recommender system

KW - diversity

KW - Recommender System

KW - movie recommendation

KW - user clustering

KW - diversification

U2 - 10.1145/3184558.3191580

DO - 10.1145/3184558.3191580

M3 - Article in proceeding

SP - 1381

EP - 1389

BT - WWW '18 Companion Proceedings of the The Web Conference 2018

PB - Association for Computing Machinery

ER -

Zanitti M, Kosta S, Sørensen JK. A User-Centric Diversity by Design Recommender System for the Movie Application Domain. In WWW '18 Companion Proceedings of the The Web Conference 2018. Association for Computing Machinery. 2018. p. 1381-1389 https://doi.org/10.1145/3184558.3191580