Assessing Viewpoint Diversity in Search Results Using Ranking Fairness Metrics

Tim Draws; Nava Tintarev; Ujwal Gadiraju; Alessandro Bozzon; Benjamin Timmermans

doi:10.1145/3468507.3468515

Assessing Viewpoint Diversity in Search Results Using Ranking Fairness Metrics

Tim Draws, Nava Tintarev, Ujwal Gadiraju, Alessandro Bozzon, Benjamin Timmermans

Research output: Chapter in Book/Conference proceedings/Edited volume › Conference contribution › Scientific › peer-review

18 Downloads (Pure)

Abstract

The way pages are ranked in search results influences whether the users of search engines are exposed to more homogeneous, or rather to more diverse viewpoints. However, this viewpoint diversity is not trivial to assess. In this paper we use existing and novel ranking fairness metrics to evaluate viewpoint diversity in search result rankings. We conduct a controlled simulation study that shows how ranking fairness metrics can be used for viewpoint diversity, how their outcome should be interpreted, and which metric is most suitable depending on the situation. This pa- per lays out important ground work for future research to measure and assess viewpoint diversity in real search result rankings.

Original language	English
Title of host publication	ACM SIGKDD Explorations Newsletter
Pages	50–58
Number of pages	9
Volume	23
Edition	1
DOIs	https://doi.org/10.1145/3468507.3468515
Publication status	Published - 2021

Bibliographical note

Green Open Access added to TU Delft Institutional Repository ‘You share, we take care!’ – Taverne project https://www.openaccess.nl/en/you-share-we-take-care
Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.

Keywords

viewpoint diversity
web search
ranking fairness

Access to Document

10.1145/3468507.3468515

3468507.3468515Final published version, 934 KB

Cite this

@inproceedings{ba940ff1fc7745d59abbb1afcbabb3ce,

title = "Assessing Viewpoint Diversity in Search Results Using Ranking Fairness Metrics",

abstract = "The way pages are ranked in search results influences whether the users of search engines are exposed to more homogeneous, or rather to more diverse viewpoints. However, this viewpoint diversity is not trivial to assess. In this paper we use existing and novel ranking fairness metrics to evaluate viewpoint diversity in search result rankings. We conduct a controlled simulation study that shows how ranking fairness metrics can be used for viewpoint diversity, how their outcome should be interpreted, and which metric is most suitable depending on the situation. This pa- per lays out important ground work for future research to measure and assess viewpoint diversity in real search result rankings.",

keywords = "viewpoint diversity, web search, ranking fairness",

author = "Tim Draws and Nava Tintarev and Ujwal Gadiraju and Alessandro Bozzon and Benjamin Timmermans",

note = "Green Open Access added to TU Delft Institutional Repository {\textquoteleft}You share, we take care!{\textquoteright} – Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public. ",

year = "2021",

doi = "10.1145/3468507.3468515",

language = "English",

volume = "23",

pages = "50–58",

booktitle = "ACM SIGKDD Explorations Newsletter",

edition = "1",

}

TY - GEN

T1 - Assessing Viewpoint Diversity in Search Results Using Ranking Fairness Metrics

AU - Draws, Tim

AU - Tintarev, Nava

AU - Gadiraju, Ujwal

AU - Bozzon, Alessandro

AU - Timmermans, Benjamin

N1 - Green Open Access added to TU Delft Institutional Repository ‘You share, we take care!’ – Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.

PY - 2021

Y1 - 2021

N2 - The way pages are ranked in search results influences whether the users of search engines are exposed to more homogeneous, or rather to more diverse viewpoints. However, this viewpoint diversity is not trivial to assess. In this paper we use existing and novel ranking fairness metrics to evaluate viewpoint diversity in search result rankings. We conduct a controlled simulation study that shows how ranking fairness metrics can be used for viewpoint diversity, how their outcome should be interpreted, and which metric is most suitable depending on the situation. This pa- per lays out important ground work for future research to measure and assess viewpoint diversity in real search result rankings.

AB - The way pages are ranked in search results influences whether the users of search engines are exposed to more homogeneous, or rather to more diverse viewpoints. However, this viewpoint diversity is not trivial to assess. In this paper we use existing and novel ranking fairness metrics to evaluate viewpoint diversity in search result rankings. We conduct a controlled simulation study that shows how ranking fairness metrics can be used for viewpoint diversity, how their outcome should be interpreted, and which metric is most suitable depending on the situation. This pa- per lays out important ground work for future research to measure and assess viewpoint diversity in real search result rankings.

KW - viewpoint diversity

KW - web search

KW - ranking fairness

U2 - 10.1145/3468507.3468515

DO - 10.1145/3468507.3468515

M3 - Conference contribution

VL - 23

SP - 50

EP - 58

BT - ACM SIGKDD Explorations Newsletter

ER -

Assessing Viewpoint Diversity in Search Results Using Ranking Fairness Metrics

Abstract

Bibliographical note

Keywords

Access to Document

Fingerprint

Cite this