Viewpoint Diversity in Search Results

Tim Draws; Nirmal Roy; Oana Inel; Alisa Rieger; Rishav Hada; Mehmet Orcun Yalcin; Benjamin Timmermans; Nava Tintarev

doi:10.1007/978-3-031-28244-7_18

Viewpoint Diversity in Search Results

Tim Draws^*, Nirmal Roy, Oana Inel, Alisa Rieger, Rishav Hada, Mehmet Orcun Yalcin, Benjamin Timmermans, Nava Tintarev

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Chapter › Academic

170 Downloads (Pure)

Abstract

Adverse phenomena such as the search engine manipulation effect (SEME), where web search users change their attitude on a topic following whatever most highly-ranked search results promote, represent crucial challenges for research and industry. However, the current lack of automatic methods to comprehensively measure or increase viewpoint diversity in search results complicates the understanding and mitigation of such effects. This paper proposes a viewpoint bias metric that evaluates the divergence from a pre-defined scenario of ideal viewpoint diversity considering two essential viewpoint dimensions (i.e., stance and logic of evaluation). In a case study, we apply this metric to actual search results and find considerable viewpoint bias in search results across queries, topics, and search engines that could lead to adverse effects such as SEME. We subsequently demonstrate that viewpoint diversity in search results can be dramatically increased using existing diversification algorithms. The methods proposed in this paper can assist researchers and practitioners in evaluating and improving viewpoint diversity in search results.

Original language	English
Title of host publication	Advances in Information Retrieval - 45th European Conference on Information Retrieval, ECIR 2023, Proceedings
Subtitle of host publication	Proceedings Part 1 ECIR 2023: European Conference on Information Retrieval
Editors	Jaap Kamps, Lorraine Goeuriot, Fabio Crestani, Maria Maistro, Hideo Joho, Brian Davis, Cathal Gurrin, Annalina Caputo, Udo Kruschwitz
Publisher	Springer International Publishing AG
Pages	279-297
Number of pages	19
Volume	13980
ISBN (Electronic)	978-3-031-28244-7
ISBN (Print)	978-3-031-28243-0
DOIs	https://doi.org/10.1007/978-3-031-28244-7_18
Publication status	Published - 2023
Event	The 45th European Conference on Information Retrieval (ECIR) - Dublin, Ireland Duration: 2 Apr 2023 → 6 Apr 2023 https://ecir2023.org/

Publication series

Series	Lecture Notes in Computer Science
Volume	13980
ISSN	0302-9743

Conference

Conference	The 45th European Conference on Information Retrieval (ECIR)
Abbreviated title	ECIR 2023
Country/Territory	Ireland
City	Dublin
Period	2/04/23 → 6/04/23
Internet address	https://ecir2023.org/

Keywords

Adapters
Checkworthiness detection
Fact-checking
Mutilingual

Access to Document

10.1007/978-3-031-28244-7_18

Full TextFinal published version, 435 KBLicence: Taverne

Cite this

Draws, T., Roy, N., Inel, O., Rieger, A., Hada, R., Yalcin, M. O., Timmermans, B., & Tintarev, N. (2023). Viewpoint Diversity in Search Results. In J. Kamps, L. Goeuriot, F. Crestani, M. Maistro, H. Joho, B. Davis, C. Gurrin, A. Caputo, & U. Kruschwitz (Eds.), Advances in Information Retrieval - 45th European Conference on Information Retrieval, ECIR 2023, Proceedings: Proceedings Part 1 ECIR 2023: European Conference on Information Retrieval (Vol. 13980, pp. 279-297). Springer International Publishing AG. https://doi.org/10.1007/978-3-031-28244-7_18

Draws, Tim ; Roy, Nirmal ; Inel, Oana et al. / Viewpoint Diversity in Search Results. Advances in Information Retrieval - 45th European Conference on Information Retrieval, ECIR 2023, Proceedings: Proceedings Part 1 ECIR 2023: European Conference on Information Retrieval. editor / Jaap Kamps ; Lorraine Goeuriot ; Fabio Crestani ; Maria Maistro ; Hideo Joho ; Brian Davis ; Cathal Gurrin ; Annalina Caputo ; Udo Kruschwitz. Vol. 13980 Springer International Publishing AG, 2023. pp. 279-297 (Lecture Notes in Computer Science, Vol. 13980).

@inbook{b7767a134e9d47919107e6b2758dd753,

title = "Viewpoint Diversity in Search Results",

abstract = "Adverse phenomena such as the search engine manipulation effect (SEME), where web search users change their attitude on a topic following whatever most highly-ranked search results promote, represent crucial challenges for research and industry. However, the current lack of automatic methods to comprehensively measure or increase viewpoint diversity in search results complicates the understanding and mitigation of such effects. This paper proposes a viewpoint bias metric that evaluates the divergence from a pre-defined scenario of ideal viewpoint diversity considering two essential viewpoint dimensions (i.e., stance and logic of evaluation). In a case study, we apply this metric to actual search results and find considerable viewpoint bias in search results across queries, topics, and search engines that could lead to adverse effects such as SEME. We subsequently demonstrate that viewpoint diversity in search results can be dramatically increased using existing diversification algorithms. The methods proposed in this paper can assist researchers and practitioners in evaluating and improving viewpoint diversity in search results.",

keywords = "Adapters, Checkworthiness detection, Fact-checking, Mutilingual",

author = "Tim Draws and Nirmal Roy and Oana Inel and Alisa Rieger and Rishav Hada and Yalcin, {Mehmet Orcun} and Benjamin Timmermans and Nava Tintarev",

note = "Funding Information: Acknowledgements. This activity is financed by IBM and the Allowance for Top Consortia for Knowledge and Innovation (TKI{\textquoteright}s) of the Dutch ministry of economic affairs. Publisher Copyright: {\textcopyright} 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.; The 45th European Conference on Information Retrieval (ECIR), ECIR 2023 ; Conference date: 02-04-2023 Through 06-04-2023",

year = "2023",

doi = "10.1007/978-3-031-28244-7_18",

language = "English",

isbn = "978-3-031-28243-0",

volume = "13980",

series = "Lecture Notes in Computer Science",

publisher = "Springer International Publishing AG",

pages = "279--297",

editor = "Jaap Kamps and Lorraine Goeuriot and Fabio Crestani and Maria Maistro and Hideo Joho and Brian Davis and Cathal Gurrin and Annalina Caputo and Udo Kruschwitz",

booktitle = "Advances in Information Retrieval - 45th European Conference on Information Retrieval, ECIR 2023, Proceedings",

url = "https://ecir2023.org/",

}

Draws, T, Roy, N, Inel, O, Rieger, A, Hada, R, Yalcin, MO, Timmermans, B & Tintarev, N 2023, Viewpoint Diversity in Search Results. in J Kamps, L Goeuriot, F Crestani, M Maistro, H Joho, B Davis, C Gurrin, A Caputo & U Kruschwitz (eds), Advances in Information Retrieval - 45th European Conference on Information Retrieval, ECIR 2023, Proceedings: Proceedings Part 1 ECIR 2023: European Conference on Information Retrieval. vol. 13980, Springer International Publishing AG, Lecture Notes in Computer Science, vol. 13980, pp. 279-297, The 45th European Conference on Information Retrieval (ECIR), Dublin, Ireland, 2/04/23. https://doi.org/10.1007/978-3-031-28244-7_18

Viewpoint Diversity in Search Results. / Draws, Tim; Roy, Nirmal; Inel, Oana et al.
Advances in Information Retrieval - 45th European Conference on Information Retrieval, ECIR 2023, Proceedings: Proceedings Part 1 ECIR 2023: European Conference on Information Retrieval. ed. / Jaap Kamps; Lorraine Goeuriot; Fabio Crestani; Maria Maistro; Hideo Joho; Brian Davis; Cathal Gurrin; Annalina Caputo; Udo Kruschwitz. Vol. 13980 Springer International Publishing AG, 2023. p. 279-297 (Lecture Notes in Computer Science, Vol. 13980).

Research output: Chapter in Book/Report/Conference proceeding › Chapter › Academic

TY - CHAP

T1 - Viewpoint Diversity in Search Results

AU - Draws, Tim

AU - Roy, Nirmal

AU - Inel, Oana

AU - Rieger, Alisa

AU - Hada, Rishav

AU - Yalcin, Mehmet Orcun

AU - Timmermans, Benjamin

AU - Tintarev, Nava

N1 - Funding Information: Acknowledgements. This activity is financed by IBM and the Allowance for Top Consortia for Knowledge and Innovation (TKI’s) of the Dutch ministry of economic affairs. Publisher Copyright: © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

PY - 2023

Y1 - 2023

N2 - Adverse phenomena such as the search engine manipulation effect (SEME), where web search users change their attitude on a topic following whatever most highly-ranked search results promote, represent crucial challenges for research and industry. However, the current lack of automatic methods to comprehensively measure or increase viewpoint diversity in search results complicates the understanding and mitigation of such effects. This paper proposes a viewpoint bias metric that evaluates the divergence from a pre-defined scenario of ideal viewpoint diversity considering two essential viewpoint dimensions (i.e., stance and logic of evaluation). In a case study, we apply this metric to actual search results and find considerable viewpoint bias in search results across queries, topics, and search engines that could lead to adverse effects such as SEME. We subsequently demonstrate that viewpoint diversity in search results can be dramatically increased using existing diversification algorithms. The methods proposed in this paper can assist researchers and practitioners in evaluating and improving viewpoint diversity in search results.

AB - Adverse phenomena such as the search engine manipulation effect (SEME), where web search users change their attitude on a topic following whatever most highly-ranked search results promote, represent crucial challenges for research and industry. However, the current lack of automatic methods to comprehensively measure or increase viewpoint diversity in search results complicates the understanding and mitigation of such effects. This paper proposes a viewpoint bias metric that evaluates the divergence from a pre-defined scenario of ideal viewpoint diversity considering two essential viewpoint dimensions (i.e., stance and logic of evaluation). In a case study, we apply this metric to actual search results and find considerable viewpoint bias in search results across queries, topics, and search engines that could lead to adverse effects such as SEME. We subsequently demonstrate that viewpoint diversity in search results can be dramatically increased using existing diversification algorithms. The methods proposed in this paper can assist researchers and practitioners in evaluating and improving viewpoint diversity in search results.

KW - Adapters

KW - Checkworthiness detection

KW - Fact-checking

KW - Mutilingual

U2 - 10.1007/978-3-031-28244-7_18

DO - 10.1007/978-3-031-28244-7_18

M3 - Chapter

SN - 978-3-031-28243-0

VL - 13980

T3 - Lecture Notes in Computer Science

SP - 279

EP - 297

BT - Advances in Information Retrieval - 45th European Conference on Information Retrieval, ECIR 2023, Proceedings

A2 - Kamps, Jaap

A2 - Goeuriot, Lorraine

A2 - Crestani, Fabio

A2 - Maistro, Maria

A2 - Joho, Hideo

A2 - Davis, Brian

A2 - Gurrin, Cathal

A2 - Caputo, Annalina

A2 - Kruschwitz, Udo

PB - Springer International Publishing AG

T2 - The 45th European Conference on Information Retrieval (ECIR)

Y2 - 2 April 2023 through 6 April 2023

ER -

Draws T, Roy N, Inel O, Rieger A, Hada R, Yalcin MO et al. Viewpoint Diversity in Search Results. In Kamps J, Goeuriot L, Crestani F, Maistro M, Joho H, Davis B, Gurrin C, Caputo A, Kruschwitz U, editors, Advances in Information Retrieval - 45th European Conference on Information Retrieval, ECIR 2023, Proceedings: Proceedings Part 1 ECIR 2023: European Conference on Information Retrieval. Vol. 13980. Springer International Publishing AG. 2023. p. 279-297. (Lecture Notes in Computer Science, Vol. 13980). doi: 10.1007/978-3-031-28244-7_18

Viewpoint Diversity in Search Results

Abstract

Publication series

Conference

Keywords

Access to Document

Fingerprint

Cite this