Are we human, or are we users? The role of natural language processing in human-centric news recommenders that nudge users to diverse content

Myrthe Reuver; Nicolas Mattis; Marijn Sax; Suzan Verberne; Nava Tintarev; Natali Helberger; Judith Moeller; Sanne Vrijenhoek; Antske Fokkens; Wouter van Atteveldt

doi:10.18653/v1/2021.nlp4posimpact-1.6

Are we human, or are we users? The role of natural language processing in human-centric news recommenders that nudge users to diverse content

Myrthe Reuver^*, Nicolas Mattis, Marijn Sax, Suzan Verberne, Nava Tintarev, Natali Helberger, Judith Moeller, Sanne Vrijenhoek, Antske Fokkens, Wouter van Atteveldt

^*Corresponding author for this work

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

136 Downloads (Pure)

Abstract

In this position paper, we present a research agenda and ideas for facilitating exposure to diverse viewpoints in news recommendation. Recommending news from diverse viewpoints is important to prevent potential filter bubble effects in news consumption, and stimulate a healthy democratic debate. To account for the complexity that is inherent to humans as citizens in a democracy, we anticipate (among others) individual-level differences in acceptance of diversity. We connect this idea to techniques in Natural Language Processing, where distributional language models would allow us to place different users and news articles in a multi-dimensional space based on semantic content, where diversity is operationalized as distance and variance. In this way, we can model individual "latitudes of diversity" for different users, and thus personalize viewpoint diversity in support of a healthy public debate. In addition, we identify technical, ethical and conceptual issues related to our presented ideas. Our investigation describes how NLP can play a central role in diversifying news recommendations.

Original language	English
Title of host publication	Proceedings of the 1ste Workshop on NLP for Positive Impact
Publisher	Association for Computational Linguistics
Pages	47-59
Number of pages	13
Edition	August 2021
ISBN (Print)	9781954085695
DOIs	https://doi.org/10.18653/v1/2021.nlp4posimpact-1.6
Publication status	Published - 2021
Event	1st Workshop on NLP for Positive Impact - Online, Unknown Duration: 5 Aug 2021 → 5 Aug 2021 https://sites.google.com/view/nlp4positiveimpact2021/#h.96h3ezqanikw

Workshop

Workshop	1st Workshop on NLP for Positive Impact
Country/Territory	Unknown
Period	5/08/21 → 5/08/21
Internet address	https://sites.google.com/view/nlp4positiveimpact2021/#h.96h3ezqanikw

Keywords

EXPOSURE DIVERSITY
DEMOCRACY

Access to Document

10.18653/v1/2021.nlp4posimpact-1.6Licence: CC BY

Full text Final published version, 260 KBLicence: Taverne
Full text Final published version, 260 KBLicence: Taverne

Cite this

Reuver, M., Mattis, N., Sax, M., Verberne, S., Tintarev, N., Helberger, N., Moeller, J., Vrijenhoek, S., Fokkens, A., & van Atteveldt, W. (2021). Are we human, or are we users? The role of natural language processing in human-centric news recommenders that nudge users to diverse content. In Proceedings of the 1ste Workshop on NLP for Positive Impact (August 2021 ed., pp. 47-59). Association for Computational Linguistics. https://doi.org/10.18653/v1/2021.nlp4posimpact-1.6

@inproceedings{2aa2e76528534566ada016552e919828,

title = "Are we human, or are we users? The role of natural language processing in human-centric news recommenders that nudge users to diverse content",

abstract = "In this position paper, we present a research agenda and ideas for facilitating exposure to diverse viewpoints in news recommendation. Recommending news from diverse viewpoints is important to prevent potential filter bubble effects in news consumption, and stimulate a healthy democratic debate. To account for the complexity that is inherent to humans as citizens in a democracy, we anticipate (among others) individual-level differences in acceptance of diversity. We connect this idea to techniques in Natural Language Processing, where distributional language models would allow us to place different users and news articles in a multi-dimensional space based on semantic content, where diversity is operationalized as distance and variance. In this way, we can model individual {"}latitudes of diversity{"} for different users, and thus personalize viewpoint diversity in support of a healthy public debate. In addition, we identify technical, ethical and conceptual issues related to our presented ideas. Our investigation describes how NLP can play a central role in diversifying news recommendations.",

keywords = "EXPOSURE DIVERSITY, DEMOCRACY",

author = "Myrthe Reuver and Nicolas Mattis and Marijn Sax and Suzan Verberne and Nava Tintarev and Natali Helberger and Judith Moeller and Sanne Vrijenhoek and Antske Fokkens and {van Atteveldt}, Wouter",

year = "2021",

doi = "10.18653/v1/2021.nlp4posimpact-1.6",

language = "English",

isbn = "9781954085695",

pages = "47--59",

booktitle = "Proceedings of the 1ste Workshop on NLP for Positive Impact",

publisher = "Association for Computational Linguistics",

edition = "August 2021",

note = "1st Workshop on NLP for Positive Impact ; Conference date: 05-08-2021 Through 05-08-2021",

url = "https://sites.google.com/view/nlp4positiveimpact2021/#h.96h3ezqanikw",

}

Reuver, M, Mattis, N, Sax, M, Verberne, S, Tintarev, N, Helberger, N, Moeller, J, Vrijenhoek, S, Fokkens, A & van Atteveldt, W 2021, Are we human, or are we users? The role of natural language processing in human-centric news recommenders that nudge users to diverse content. in Proceedings of the 1ste Workshop on NLP for Positive Impact. August 2021 edn, Association for Computational Linguistics, pp. 47-59, 1st Workshop on NLP for Positive Impact, Unknown, 5/08/21. https://doi.org/10.18653/v1/2021.nlp4posimpact-1.6

Are we human, or are we users? The role of natural language processing in human-centric news recommenders that nudge users to diverse content. / Reuver, Myrthe; Mattis, Nicolas; Sax, Marijn et al.
Proceedings of the 1ste Workshop on NLP for Positive Impact. August 2021. ed. Association for Computational Linguistics, 2021. p. 47-59.

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

TY - GEN

T1 - Are we human, or are we users? The role of natural language processing in human-centric news recommenders that nudge users to diverse content

AU - Reuver, Myrthe

AU - Mattis, Nicolas

AU - Sax, Marijn

AU - Verberne, Suzan

AU - Tintarev, Nava

AU - Helberger, Natali

AU - Moeller, Judith

AU - Vrijenhoek, Sanne

AU - Fokkens, Antske

AU - van Atteveldt, Wouter

PY - 2021

Y1 - 2021

N2 - In this position paper, we present a research agenda and ideas for facilitating exposure to diverse viewpoints in news recommendation. Recommending news from diverse viewpoints is important to prevent potential filter bubble effects in news consumption, and stimulate a healthy democratic debate. To account for the complexity that is inherent to humans as citizens in a democracy, we anticipate (among others) individual-level differences in acceptance of diversity. We connect this idea to techniques in Natural Language Processing, where distributional language models would allow us to place different users and news articles in a multi-dimensional space based on semantic content, where diversity is operationalized as distance and variance. In this way, we can model individual "latitudes of diversity" for different users, and thus personalize viewpoint diversity in support of a healthy public debate. In addition, we identify technical, ethical and conceptual issues related to our presented ideas. Our investigation describes how NLP can play a central role in diversifying news recommendations.

AB - In this position paper, we present a research agenda and ideas for facilitating exposure to diverse viewpoints in news recommendation. Recommending news from diverse viewpoints is important to prevent potential filter bubble effects in news consumption, and stimulate a healthy democratic debate. To account for the complexity that is inherent to humans as citizens in a democracy, we anticipate (among others) individual-level differences in acceptance of diversity. We connect this idea to techniques in Natural Language Processing, where distributional language models would allow us to place different users and news articles in a multi-dimensional space based on semantic content, where diversity is operationalized as distance and variance. In this way, we can model individual "latitudes of diversity" for different users, and thus personalize viewpoint diversity in support of a healthy public debate. In addition, we identify technical, ethical and conceptual issues related to our presented ideas. Our investigation describes how NLP can play a central role in diversifying news recommendations.

KW - EXPOSURE DIVERSITY

KW - DEMOCRACY

U2 - 10.18653/v1/2021.nlp4posimpact-1.6

DO - 10.18653/v1/2021.nlp4posimpact-1.6

M3 - Conference article in proceeding

SN - 9781954085695

SP - 47

EP - 59

BT - Proceedings of the 1ste Workshop on NLP for Positive Impact

PB - Association for Computational Linguistics

T2 - 1st Workshop on NLP for Positive Impact

Y2 - 5 August 2021 through 5 August 2021

ER -

Reuver M, Mattis N, Sax M, Verberne S, Tintarev N, Helberger N et al. Are we human, or are we users? The role of natural language processing in human-centric news recommenders that nudge users to diverse content. In Proceedings of the 1ste Workshop on NLP for Positive Impact. August 2021 ed. Association for Computational Linguistics. 2021. p. 47-59 doi: 10.18653/v1/2021.nlp4posimpact-1.6