Public Service Media, Diversity and Algorithmic Recommendation: Tensions between Editorial Principles and Algorithms in European PSM Organizations

Publikation: Konferencebidrag uden forlag/tidsskriftKonferenceabstrakt til konferenceForskningpeer review

Resumé

Public Service Media (PSM) websites are an interesting case for the implementation of recommender systems for media personaliza- tion, as the PSM organizations need to balance the optimization of exposure with traditional but ill-de ned PSM policy goals such as fairness, viewpoint diversity and transparency. Furthermore, the mathematical logic of recommender system needs to be adapted to the legacy broadcasting scheduling and publishing strategies and procedures. Finally, as the PSM organizations step into new territories, a domestication and adaption of the recommender sys- tem technologies must take place while PSM organizations try to embrace the new knowledge and new professions associated with recommender systems. Based on 25 in-depth interviews, conducted December 2016 to April 2019, this paper presents a cross-European analysis of the implementation of recommender systems in nine European public service media organizations from eight countries. The ndings indicate that PSM organizations, although seeing per- sonalisation as competitive necessity, approach recommendation systems with hesitation in order to maintain core PSM-values in the online environment. Furthermore, although the CF recommender technologies chosen indicate a user-centered approach, curation systems on top of recommender systems re-install a broadcaster- centric approach.
OriginalsprogEngelsk
Publikationsdato2019
StatusUdgivet - 2019
BegivenhedRecSys 2019: 13th ACM Conference on Recommender Systems - Copenhagen, Denmark, Copenhagen, Danmark
Varighed: 16 sep. 201820 sep. 2018
Konferencens nummer: 13
http://recsys.acm.org/recsys19

Konference

KonferenceRecSys 2019: 13th ACM Conference on Recommender Systems
Nummer13
LokationCopenhagen, Denmark
LandDanmark
ByCopenhagen
Periode16/09/201820/09/2018
Internetadresse

Fingerprint

public service
personalization
media policy
broadcaster
logic
broadcasting
fairness
transparency
scheduling
website
profession
interview
knowledge
Values

Emneord

  • public service media
  • personalization
  • algorithmic recommendation

Citer dette

@conference{82456676adda48b795be1f1e255c0a7a,
title = "Public Service Media, Diversity and Algorithmic Recommendation: Tensions between Editorial Principles and Algorithms in European PSM Organizations",
abstract = "Public Service Media (PSM) websites are an interesting case for the implementation of recommender systems for media personaliza- tion, as the PSM organizations need to balance the optimization of exposure with traditional but ill-de ned PSM policy goals such as fairness, viewpoint diversity and transparency. Furthermore, the mathematical logic of recommender system needs to be adapted to the legacy broadcasting scheduling and publishing strategies and procedures. Finally, as the PSM organizations step into new territories, domestication and adaption of the recommender sys- tem technologies must take place while PSM organizations try to embrace the new knowledge and new professions associated with recommender systems. Based on 25 in-depth interviews conducted from December 2016 to April 2019, this paper presents a cross- European analysis of the implementation of recommender systems in nine European public service media organizations from eight countries. The ndings indicate that PSM organizations, although viewing personalisation as competitive necessity, approach rec- ommendation systems with hesitation in order to maintain core PSM-values in the online environment. Furthermore, although the collaborative ltering chosen by the PSM organizations indicate a user-centered approach, curation systems on top of recommender systems re-install a broadcaster-centric approach.",
keywords = "public service media, personalization, algorithmic recommendation, public service media, personalisation, recommender system, diversity, implementation",
author = "S{\o}rensen, {Jannick Kirk}",
note = "Workshop paper for 7th International Workshop on News Recommendation and Analytics (INRA 2019) conducted as part of RecSys 2019; RecSys 2019: 13th ACM Conference on Recommender Systems, RecSys 2019 ; Conference date: 16-09-2018 Through 20-09-2018",
year = "2019",
language = "English",
url = "http://recsys.acm.org/recsys19",

}

Sørensen, JK 2019, 'Public Service Media, Diversity and Algorithmic Recommendation: Tensions between Editorial Principles and Algorithms in European PSM Organizations', RecSys 2019: 13th ACM Conference on Recommender Systems, Copenhagen, Danmark, 16/09/2018 - 20/09/2018.

Public Service Media, Diversity and Algorithmic Recommendation : Tensions between Editorial Principles and Algorithms in European PSM Organizations. / Sørensen, Jannick Kirk.

2019. Abstract fra RecSys 2019: 13th ACM Conference on Recommender Systems, Copenhagen, Danmark.

Publikation: Konferencebidrag uden forlag/tidsskriftKonferenceabstrakt til konferenceForskningpeer review

TY - ABST

T1 - Public Service Media, Diversity and Algorithmic Recommendation

T2 - Tensions between Editorial Principles and Algorithms in European PSM Organizations

AU - Sørensen, Jannick Kirk

N1 - Workshop paper for 7th International Workshop on News Recommendation and Analytics (INRA 2019) conducted as part of RecSys 2019

PY - 2019

Y1 - 2019

N2 - Public Service Media (PSM) websites are an interesting case for the implementation of recommender systems for media personaliza- tion, as the PSM organizations need to balance the optimization of exposure with traditional but ill-de ned PSM policy goals such as fairness, viewpoint diversity and transparency. Furthermore, the mathematical logic of recommender system needs to be adapted to the legacy broadcasting scheduling and publishing strategies and procedures. Finally, as the PSM organizations step into new territories, domestication and adaption of the recommender sys- tem technologies must take place while PSM organizations try to embrace the new knowledge and new professions associated with recommender systems. Based on 25 in-depth interviews conducted from December 2016 to April 2019, this paper presents a cross- European analysis of the implementation of recommender systems in nine European public service media organizations from eight countries. The ndings indicate that PSM organizations, although viewing personalisation as competitive necessity, approach rec- ommendation systems with hesitation in order to maintain core PSM-values in the online environment. Furthermore, although the collaborative ltering chosen by the PSM organizations indicate a user-centered approach, curation systems on top of recommender systems re-install a broadcaster-centric approach.

AB - Public Service Media (PSM) websites are an interesting case for the implementation of recommender systems for media personaliza- tion, as the PSM organizations need to balance the optimization of exposure with traditional but ill-de ned PSM policy goals such as fairness, viewpoint diversity and transparency. Furthermore, the mathematical logic of recommender system needs to be adapted to the legacy broadcasting scheduling and publishing strategies and procedures. Finally, as the PSM organizations step into new territories, domestication and adaption of the recommender sys- tem technologies must take place while PSM organizations try to embrace the new knowledge and new professions associated with recommender systems. Based on 25 in-depth interviews conducted from December 2016 to April 2019, this paper presents a cross- European analysis of the implementation of recommender systems in nine European public service media organizations from eight countries. The ndings indicate that PSM organizations, although viewing personalisation as competitive necessity, approach rec- ommendation systems with hesitation in order to maintain core PSM-values in the online environment. Furthermore, although the collaborative ltering chosen by the PSM organizations indicate a user-centered approach, curation systems on top of recommender systems re-install a broadcaster-centric approach.

KW - public service media

KW - personalization

KW - algorithmic recommendation

KW - public service media

KW - personalisation

KW - recommender system

KW - diversity

KW - implementation

M3 - Conference abstract for conference

ER -