SlideShare a Scribd company logo
1 of 14
1
WIS
Web
Information
Systems
Assessing Viewpoint Diversity
in Search Results Using
Ranking Fairness Metrics
Tim Draws1, Nava Tintarev1, Ujwal
Gadiraju1, Alessandro Bozzon1, and
Benjamin Timmermans2
1TU Delft, The Netherlands
2IBM, The Netherlands t.a.draws@tudelft.nl
2
WIS
Web
Information
Systems
Biases in web search
• Position bias2-4
• “Search Engine Manipulation Effect”1,5
How can we quantify (a lack of) viewpoint
diversity in search results?
Yes!
Yes!
Yes!
Yes!
Yes!
No!
No!
3
WIS
Web
Information
Systems
Ranking fairness metrics
Statistical parity in fair ranking: protected
attribute should not influence the ranking6
evaluate statistical parity for top i
discount by rank
normalize
4
WIS
Web
Information
Systems
Our paper
RQ:
Can ranking fairness metrics be used to assess
viewpoint diversity in search results?
Contributions:
1. Evaluation of existing metrics
2. Novel metric
7
WIS
Web
Information
Systems
Representing viewpoints
Should we all be vegan?
Strongly
opposing
Opposing Somewhat
opposing
Neutral Somewhat
supporting
Supporting Strongly
supporting
protected non-protected
Binomial viewpoint fairness
8
WIS
Web
Information
Systems
Representing viewpoints
Should we all be vegan?
Strongly
opposing
Opposing Somewhat
opposing
Neutral Somewhat
supporting
Supporting Strongly
supporting
protected
Multinomial viewpoint fairness
9
WIS
Web
Information
Systems
Metrics we consider
Binomial viewpoint fairness
– Normalized Discounted Difference (nDD)6
– Normalized Discounted Ratio (nDR)6
– Normalized Discounted Kullback-Leibler Divergence (nDKL)6
Multinomial viewpoint fairness
– Normalized Discounted Jensen-Shannon Divergence (nDJS)
11
WIS
Web
Information
Systems
Simulation studies
How do the metrics behave for different
levels of viewpoint diversity?
• Three synthetic data sets S1, S2, S3
• Per set created rankings to simulate different
levels of viewpoint diversity
13
WIS
Web
Information
Systems
Weighted sampling procedure
Rank Viewpoint
1 Strongly opposing
2 Strongly opposing
3 Opposing
4 Somewhat opposing
5 Supporting
6 Strongly opposing
… …
S1
sampling
Per set: created rankings with different levels of ranking bias
• Binomial viewpoint fairness: all opposing viewpoints get w1, all others w2
• Multinomial viewpoint fairness: random viewpoint get w1, all others w2
14
WIS
Web
Information
Systems
Results: binomial viewpoint fairness
nDD nDR nDKL
−1.0 −0.8 −0.6 −0.4 −0.2 0.0 0.2 0.4 0.6 0.8 1.0 −1.0 −0.8 −0.6 −0.4 −0.2 0.0 0.2 0.4 0.6 0.8 1.0 −1.0 −0.8 −0.6 −0.4 −0.2 0.0 0.2 0.4 0.6 0.8 1.0
0.0
0.1
0.2
0.3
0.4
0.5
0.6
0.7
0.8
0.9
1.0
Ranking bias
Meanmetricvalue
Distribution S1 S2 S3
• All metrics assess binomial viewpoint fairness (as expected)
• All metrics are asymmetric (proportion of protected items and
”direction” of bias matter)
• Which metric to use depends on strength of ranking bias
15
WIS
Web
Information
Systems
Results: multinomial viewpoint fairness
0.0
0.1
0.2
−1.0 −0.8 −0.6 −0.4 −0.2 0.0 0.2 0.4 0.6 0.8 1.0
Ranking bias
MeannDJSvalue
Distribution S1 S2 S3
• nDJS assesses multinomial viewpoint fairness
• nDJS is also asymmetric (proportion of protected items and ”direction”
of bias matter)
• Careful interpretation: values not directly comparable to other metrics
16
WIS
Web
Information
Systems
Discussion
• Metrics work for assessing viewpoint diversity
• Considerations:
– What is the underlying aim?
– How balanced is the data overall?
– How strong is the ranking bias?
– What is the direction of ranking bias?
17
WIS
Web
Information
Systems
Take home and future work
• Ranking fairness metrics can be used for
assessing viewpoint diversity in search results
– (when interpreted correctly)
• Future work can use these metrics to…
– …assess viewpoint diversity in real search results
– …align different metric and behavioral outcomes
18
WIS
Web
Information
Systems
References
[1] R. Epstein and R. E. Robertson. The search engine manipulation effect (SEME) and its possible impact on the outcomes of elections. Proceedings
of the National Academy of Sciences of the United States of America, 112(33):E4512–E4521, 2015.
[2] A. Ghose, P. G. Ipeirotis, and B. Li. Examining the impact of ranking on consumer behavior and search engine revenue. Management Science,
60(7):1632–1654, 2014.
[3] L. A. Granka, T. Joachims, and G. Gay. Eye-tracking analysis of user behavior in WWW search.
Proceedings of Sheffield SIGIR - Twenty-Seventh Annual International ACM SIGIR Conference on Research and Development in Information Retrieval,
pages 478–479, 2004.
[4] B. Pan, H. Hembrooke, T. Joachims, L. Lorigo, G. Gay, and L. Granka. In Google we trust: Users’ decisions on rank, position, and relevance.
Journal of Computer-Mediated Communication, 12(3):801– 823, 2007.
[5] F. A. Pogacar, A. Ghenai, M. D. Smucker, and C. L. Clarke. The positive and negative influence of search results on people’s decisions about the
efficacy of medical treatments. ICTIR 2017 - Proceedings of the 2017 ACM SIGIR International Conference on the Theory of Information Retrieval,
pages 209– 216, 2017.
[6] Yang, K., & Stoyanovich, J. Measuring fairness in ranked outputs. Proceedings of the 29th International Conference on Scientific and Statistical
Database Management, pages 1-6, 2017.

More Related Content

Similar to Assessing Viewpoint Diversity in Search Results Using Ranking Fairness Metrics

A Computational Analysis of Agenda Setting Theory
A Computational Analysis of Agenda Setting TheoryA Computational Analysis of Agenda Setting Theory
A Computational Analysis of Agenda Setting TheoryAlice Oh
 
Navigating the Future_ Latest Data Analytics Trends in 2024 - Uncodemy (1).pdf
Navigating the Future_ Latest Data Analytics Trends in 2024 - Uncodemy (1).pdfNavigating the Future_ Latest Data Analytics Trends in 2024 - Uncodemy (1).pdf
Navigating the Future_ Latest Data Analytics Trends in 2024 - Uncodemy (1).pdfAhana Sharma
 
Data Science, Personalisation & Product management
Data Science, Personalisation & Product managementData Science, Personalisation & Product management
Data Science, Personalisation & Product managementBhaskar Krishnan
 
Subscribing to Your Critical Data Supply Chain - Getting Value from True Data...
Subscribing to Your Critical Data Supply Chain - Getting Value from True Data...Subscribing to Your Critical Data Supply Chain - Getting Value from True Data...
Subscribing to Your Critical Data Supply Chain - Getting Value from True Data...DATAVERSITY
 
A Perspective from the intersection Data Science, Mobility, and Mobile Devices
A Perspective from the intersection Data Science, Mobility, and Mobile DevicesA Perspective from the intersection Data Science, Mobility, and Mobile Devices
A Perspective from the intersection Data Science, Mobility, and Mobile DevicesYael Garten
 
Making an impact with data science
Making an impact  with data scienceMaking an impact  with data science
Making an impact with data scienceJordan Engbers
 
Thesis Presentation
Thesis PresentationThesis Presentation
Thesis Presentationnirvdrum
 
IIR 2017, Lugano Switzerland
IIR 2017, Lugano SwitzerlandIIR 2017, Lugano Switzerland
IIR 2017, Lugano SwitzerlandMarco Polignano
 
Towards Responsible AI - NY.pptx
Towards Responsible AI - NY.pptxTowards Responsible AI - NY.pptx
Towards Responsible AI - NY.pptxLuis775803
 
State of Data Governance in 2021
State of Data Governance in 2021State of Data Governance in 2021
State of Data Governance in 2021DATAVERSITY
 
EDR-8202 Statistics IIWeek 2 Assignment Worksheet C.docx
EDR-8202 Statistics IIWeek 2 Assignment Worksheet  C.docxEDR-8202 Statistics IIWeek 2 Assignment Worksheet  C.docx
EDR-8202 Statistics IIWeek 2 Assignment Worksheet C.docxtidwellveronique
 
EDR-8202 Statistics IIWeek 2 Assignment Worksheet C.docx
EDR-8202 Statistics IIWeek 2 Assignment Worksheet  C.docxEDR-8202 Statistics IIWeek 2 Assignment Worksheet  C.docx
EDR-8202 Statistics IIWeek 2 Assignment Worksheet C.docxbudabrooks46239
 
Smart Feedback Analysis System
Smart Feedback Analysis SystemSmart Feedback Analysis System
Smart Feedback Analysis SystemIRJET Journal
 
"Ready or Not, Here Comes 2015: Marketing Trends to Master" TrendLab Webinar
"Ready or Not, Here Comes 2015: Marketing Trends to Master" TrendLab Webinar"Ready or Not, Here Comes 2015: Marketing Trends to Master" TrendLab Webinar
"Ready or Not, Here Comes 2015: Marketing Trends to Master" TrendLab WebinarBluespire Marketing
 
Présentation Forrester - Forum MDM Micropole 2014
Présentation Forrester - Forum MDM Micropole 2014Présentation Forrester - Forum MDM Micropole 2014
Présentation Forrester - Forum MDM Micropole 2014Micropole Group
 
Exploratory data analysis for business MODULE 1.pptx
Exploratory data analysis for business MODULE 1.pptxExploratory data analysis for business MODULE 1.pptx
Exploratory data analysis for business MODULE 1.pptxYashwanthKumar306128
 
Software Analytics = Sharing Information
Software Analytics = Sharing InformationSoftware Analytics = Sharing Information
Software Analytics = Sharing InformationThomas Zimmermann
 
It's all about big data
It's all about big dataIt's all about big data
It's all about big dataYuxin Tu, PhD
 
Pitfalls and Countermeasures in Software Quality Measurements and Evaluations
Pitfalls and Countermeasures in Software Quality Measurements and EvaluationsPitfalls and Countermeasures in Software Quality Measurements and Evaluations
Pitfalls and Countermeasures in Software Quality Measurements and EvaluationsHironori Washizaki
 

Similar to Assessing Viewpoint Diversity in Search Results Using Ranking Fairness Metrics (20)

A Computational Analysis of Agenda Setting Theory
A Computational Analysis of Agenda Setting TheoryA Computational Analysis of Agenda Setting Theory
A Computational Analysis of Agenda Setting Theory
 
Delivering insights from Web
Delivering insights from WebDelivering insights from Web
Delivering insights from Web
 
Navigating the Future_ Latest Data Analytics Trends in 2024 - Uncodemy (1).pdf
Navigating the Future_ Latest Data Analytics Trends in 2024 - Uncodemy (1).pdfNavigating the Future_ Latest Data Analytics Trends in 2024 - Uncodemy (1).pdf
Navigating the Future_ Latest Data Analytics Trends in 2024 - Uncodemy (1).pdf
 
Data Science, Personalisation & Product management
Data Science, Personalisation & Product managementData Science, Personalisation & Product management
Data Science, Personalisation & Product management
 
Subscribing to Your Critical Data Supply Chain - Getting Value from True Data...
Subscribing to Your Critical Data Supply Chain - Getting Value from True Data...Subscribing to Your Critical Data Supply Chain - Getting Value from True Data...
Subscribing to Your Critical Data Supply Chain - Getting Value from True Data...
 
A Perspective from the intersection Data Science, Mobility, and Mobile Devices
A Perspective from the intersection Data Science, Mobility, and Mobile DevicesA Perspective from the intersection Data Science, Mobility, and Mobile Devices
A Perspective from the intersection Data Science, Mobility, and Mobile Devices
 
Making an impact with data science
Making an impact  with data scienceMaking an impact  with data science
Making an impact with data science
 
Thesis Presentation
Thesis PresentationThesis Presentation
Thesis Presentation
 
IIR 2017, Lugano Switzerland
IIR 2017, Lugano SwitzerlandIIR 2017, Lugano Switzerland
IIR 2017, Lugano Switzerland
 
Towards Responsible AI - NY.pptx
Towards Responsible AI - NY.pptxTowards Responsible AI - NY.pptx
Towards Responsible AI - NY.pptx
 
State of Data Governance in 2021
State of Data Governance in 2021State of Data Governance in 2021
State of Data Governance in 2021
 
EDR-8202 Statistics IIWeek 2 Assignment Worksheet C.docx
EDR-8202 Statistics IIWeek 2 Assignment Worksheet  C.docxEDR-8202 Statistics IIWeek 2 Assignment Worksheet  C.docx
EDR-8202 Statistics IIWeek 2 Assignment Worksheet C.docx
 
EDR-8202 Statistics IIWeek 2 Assignment Worksheet C.docx
EDR-8202 Statistics IIWeek 2 Assignment Worksheet  C.docxEDR-8202 Statistics IIWeek 2 Assignment Worksheet  C.docx
EDR-8202 Statistics IIWeek 2 Assignment Worksheet C.docx
 
Smart Feedback Analysis System
Smart Feedback Analysis SystemSmart Feedback Analysis System
Smart Feedback Analysis System
 
"Ready or Not, Here Comes 2015: Marketing Trends to Master" TrendLab Webinar
"Ready or Not, Here Comes 2015: Marketing Trends to Master" TrendLab Webinar"Ready or Not, Here Comes 2015: Marketing Trends to Master" TrendLab Webinar
"Ready or Not, Here Comes 2015: Marketing Trends to Master" TrendLab Webinar
 
Présentation Forrester - Forum MDM Micropole 2014
Présentation Forrester - Forum MDM Micropole 2014Présentation Forrester - Forum MDM Micropole 2014
Présentation Forrester - Forum MDM Micropole 2014
 
Exploratory data analysis for business MODULE 1.pptx
Exploratory data analysis for business MODULE 1.pptxExploratory data analysis for business MODULE 1.pptx
Exploratory data analysis for business MODULE 1.pptx
 
Software Analytics = Sharing Information
Software Analytics = Sharing InformationSoftware Analytics = Sharing Information
Software Analytics = Sharing Information
 
It's all about big data
It's all about big dataIt's all about big data
It's all about big data
 
Pitfalls and Countermeasures in Software Quality Measurements and Evaluations
Pitfalls and Countermeasures in Software Quality Measurements and EvaluationsPitfalls and Countermeasures in Software Quality Measurements and Evaluations
Pitfalls and Countermeasures in Software Quality Measurements and Evaluations
 

Recently uploaded

Microteaching on terms used in filtration .Pharmaceutical Engineering
Microteaching on terms used in filtration .Pharmaceutical EngineeringMicroteaching on terms used in filtration .Pharmaceutical Engineering
Microteaching on terms used in filtration .Pharmaceutical EngineeringPrajakta Shinde
 
Pests of Bengal gram_Identification_Dr.UPR.pdf
Pests of Bengal gram_Identification_Dr.UPR.pdfPests of Bengal gram_Identification_Dr.UPR.pdf
Pests of Bengal gram_Identification_Dr.UPR.pdfPirithiRaju
 
User Guide: Pulsar™ Weather Station (Columbia Weather Systems)
User Guide: Pulsar™ Weather Station (Columbia Weather Systems)User Guide: Pulsar™ Weather Station (Columbia Weather Systems)
User Guide: Pulsar™ Weather Station (Columbia Weather Systems)Columbia Weather Systems
 
Observational constraints on mergers creating magnetism in massive stars
Observational constraints on mergers creating magnetism in massive starsObservational constraints on mergers creating magnetism in massive stars
Observational constraints on mergers creating magnetism in massive starsSérgio Sacani
 
GenAI talk for Young at Wageningen University & Research (WUR) March 2024
GenAI talk for Young at Wageningen University & Research (WUR) March 2024GenAI talk for Young at Wageningen University & Research (WUR) March 2024
GenAI talk for Young at Wageningen University & Research (WUR) March 2024Jene van der Heide
 
THE ROLE OF PHARMACOGNOSY IN TRADITIONAL AND MODERN SYSTEM OF MEDICINE.pptx
THE ROLE OF PHARMACOGNOSY IN TRADITIONAL AND MODERN SYSTEM OF MEDICINE.pptxTHE ROLE OF PHARMACOGNOSY IN TRADITIONAL AND MODERN SYSTEM OF MEDICINE.pptx
THE ROLE OF PHARMACOGNOSY IN TRADITIONAL AND MODERN SYSTEM OF MEDICINE.pptxNandakishor Bhaurao Deshmukh
 
ECG Graph Monitoring with AD8232 ECG Sensor & Arduino.pptx
ECG Graph Monitoring with AD8232 ECG Sensor & Arduino.pptxECG Graph Monitoring with AD8232 ECG Sensor & Arduino.pptx
ECG Graph Monitoring with AD8232 ECG Sensor & Arduino.pptxmaryFF1
 
Microphone- characteristics,carbon microphone, dynamic microphone.pptx
Microphone- characteristics,carbon microphone, dynamic microphone.pptxMicrophone- characteristics,carbon microphone, dynamic microphone.pptx
Microphone- characteristics,carbon microphone, dynamic microphone.pptxpriyankatabhane
 
trihybrid cross , test cross chi squares
trihybrid cross , test cross chi squarestrihybrid cross , test cross chi squares
trihybrid cross , test cross chi squaresusmanzain586
 
User Guide: Capricorn FLX™ Weather Station
User Guide: Capricorn FLX™ Weather StationUser Guide: Capricorn FLX™ Weather Station
User Guide: Capricorn FLX™ Weather StationColumbia Weather Systems
 
Pests of soyabean_Binomics_IdentificationDr.UPR.pdf
Pests of soyabean_Binomics_IdentificationDr.UPR.pdfPests of soyabean_Binomics_IdentificationDr.UPR.pdf
Pests of soyabean_Binomics_IdentificationDr.UPR.pdfPirithiRaju
 
Thermodynamics ,types of system,formulae ,gibbs free energy .pptx
Thermodynamics ,types of system,formulae ,gibbs free energy .pptxThermodynamics ,types of system,formulae ,gibbs free energy .pptx
Thermodynamics ,types of system,formulae ,gibbs free energy .pptxuniversity
 
Bioteknologi kelas 10 kumer smapsa .pptx
Bioteknologi kelas 10 kumer smapsa .pptxBioteknologi kelas 10 kumer smapsa .pptx
Bioteknologi kelas 10 kumer smapsa .pptx023NiWayanAnggiSriWa
 
Pests of safflower_Binomics_Identification_Dr.UPR.pdf
Pests of safflower_Binomics_Identification_Dr.UPR.pdfPests of safflower_Binomics_Identification_Dr.UPR.pdf
Pests of safflower_Binomics_Identification_Dr.UPR.pdfPirithiRaju
 
Base editing, prime editing, Cas13 & RNA editing and organelle base editing
Base editing, prime editing, Cas13 & RNA editing and organelle base editingBase editing, prime editing, Cas13 & RNA editing and organelle base editing
Base editing, prime editing, Cas13 & RNA editing and organelle base editingNetHelix
 
《Queensland毕业文凭-昆士兰大学毕业证成绩单》
《Queensland毕业文凭-昆士兰大学毕业证成绩单》《Queensland毕业文凭-昆士兰大学毕业证成绩单》
《Queensland毕业文凭-昆士兰大学毕业证成绩单》rnrncn29
 
LIGHT-PHENOMENA-BY-CABUALDIONALDOPANOGANCADIENTE-CONDEZA (1).pptx
LIGHT-PHENOMENA-BY-CABUALDIONALDOPANOGANCADIENTE-CONDEZA (1).pptxLIGHT-PHENOMENA-BY-CABUALDIONALDOPANOGANCADIENTE-CONDEZA (1).pptx
LIGHT-PHENOMENA-BY-CABUALDIONALDOPANOGANCADIENTE-CONDEZA (1).pptxmalonesandreagweneth
 
Pests of Blackgram, greengram, cowpea_Dr.UPR.pdf
Pests of Blackgram, greengram, cowpea_Dr.UPR.pdfPests of Blackgram, greengram, cowpea_Dr.UPR.pdf
Pests of Blackgram, greengram, cowpea_Dr.UPR.pdfPirithiRaju
 

Recently uploaded (20)

Microteaching on terms used in filtration .Pharmaceutical Engineering
Microteaching on terms used in filtration .Pharmaceutical EngineeringMicroteaching on terms used in filtration .Pharmaceutical Engineering
Microteaching on terms used in filtration .Pharmaceutical Engineering
 
Pests of Bengal gram_Identification_Dr.UPR.pdf
Pests of Bengal gram_Identification_Dr.UPR.pdfPests of Bengal gram_Identification_Dr.UPR.pdf
Pests of Bengal gram_Identification_Dr.UPR.pdf
 
User Guide: Pulsar™ Weather Station (Columbia Weather Systems)
User Guide: Pulsar™ Weather Station (Columbia Weather Systems)User Guide: Pulsar™ Weather Station (Columbia Weather Systems)
User Guide: Pulsar™ Weather Station (Columbia Weather Systems)
 
Let’s Say Someone Did Drop the Bomb. Then What?
Let’s Say Someone Did Drop the Bomb. Then What?Let’s Say Someone Did Drop the Bomb. Then What?
Let’s Say Someone Did Drop the Bomb. Then What?
 
Observational constraints on mergers creating magnetism in massive stars
Observational constraints on mergers creating magnetism in massive starsObservational constraints on mergers creating magnetism in massive stars
Observational constraints on mergers creating magnetism in massive stars
 
GenAI talk for Young at Wageningen University & Research (WUR) March 2024
GenAI talk for Young at Wageningen University & Research (WUR) March 2024GenAI talk for Young at Wageningen University & Research (WUR) March 2024
GenAI talk for Young at Wageningen University & Research (WUR) March 2024
 
THE ROLE OF PHARMACOGNOSY IN TRADITIONAL AND MODERN SYSTEM OF MEDICINE.pptx
THE ROLE OF PHARMACOGNOSY IN TRADITIONAL AND MODERN SYSTEM OF MEDICINE.pptxTHE ROLE OF PHARMACOGNOSY IN TRADITIONAL AND MODERN SYSTEM OF MEDICINE.pptx
THE ROLE OF PHARMACOGNOSY IN TRADITIONAL AND MODERN SYSTEM OF MEDICINE.pptx
 
ECG Graph Monitoring with AD8232 ECG Sensor & Arduino.pptx
ECG Graph Monitoring with AD8232 ECG Sensor & Arduino.pptxECG Graph Monitoring with AD8232 ECG Sensor & Arduino.pptx
ECG Graph Monitoring with AD8232 ECG Sensor & Arduino.pptx
 
Microphone- characteristics,carbon microphone, dynamic microphone.pptx
Microphone- characteristics,carbon microphone, dynamic microphone.pptxMicrophone- characteristics,carbon microphone, dynamic microphone.pptx
Microphone- characteristics,carbon microphone, dynamic microphone.pptx
 
trihybrid cross , test cross chi squares
trihybrid cross , test cross chi squarestrihybrid cross , test cross chi squares
trihybrid cross , test cross chi squares
 
Volatile Oils Pharmacognosy And Phytochemistry -I
Volatile Oils Pharmacognosy And Phytochemistry -IVolatile Oils Pharmacognosy And Phytochemistry -I
Volatile Oils Pharmacognosy And Phytochemistry -I
 
User Guide: Capricorn FLX™ Weather Station
User Guide: Capricorn FLX™ Weather StationUser Guide: Capricorn FLX™ Weather Station
User Guide: Capricorn FLX™ Weather Station
 
Pests of soyabean_Binomics_IdentificationDr.UPR.pdf
Pests of soyabean_Binomics_IdentificationDr.UPR.pdfPests of soyabean_Binomics_IdentificationDr.UPR.pdf
Pests of soyabean_Binomics_IdentificationDr.UPR.pdf
 
Thermodynamics ,types of system,formulae ,gibbs free energy .pptx
Thermodynamics ,types of system,formulae ,gibbs free energy .pptxThermodynamics ,types of system,formulae ,gibbs free energy .pptx
Thermodynamics ,types of system,formulae ,gibbs free energy .pptx
 
Bioteknologi kelas 10 kumer smapsa .pptx
Bioteknologi kelas 10 kumer smapsa .pptxBioteknologi kelas 10 kumer smapsa .pptx
Bioteknologi kelas 10 kumer smapsa .pptx
 
Pests of safflower_Binomics_Identification_Dr.UPR.pdf
Pests of safflower_Binomics_Identification_Dr.UPR.pdfPests of safflower_Binomics_Identification_Dr.UPR.pdf
Pests of safflower_Binomics_Identification_Dr.UPR.pdf
 
Base editing, prime editing, Cas13 & RNA editing and organelle base editing
Base editing, prime editing, Cas13 & RNA editing and organelle base editingBase editing, prime editing, Cas13 & RNA editing and organelle base editing
Base editing, prime editing, Cas13 & RNA editing and organelle base editing
 
《Queensland毕业文凭-昆士兰大学毕业证成绩单》
《Queensland毕业文凭-昆士兰大学毕业证成绩单》《Queensland毕业文凭-昆士兰大学毕业证成绩单》
《Queensland毕业文凭-昆士兰大学毕业证成绩单》
 
LIGHT-PHENOMENA-BY-CABUALDIONALDOPANOGANCADIENTE-CONDEZA (1).pptx
LIGHT-PHENOMENA-BY-CABUALDIONALDOPANOGANCADIENTE-CONDEZA (1).pptxLIGHT-PHENOMENA-BY-CABUALDIONALDOPANOGANCADIENTE-CONDEZA (1).pptx
LIGHT-PHENOMENA-BY-CABUALDIONALDOPANOGANCADIENTE-CONDEZA (1).pptx
 
Pests of Blackgram, greengram, cowpea_Dr.UPR.pdf
Pests of Blackgram, greengram, cowpea_Dr.UPR.pdfPests of Blackgram, greengram, cowpea_Dr.UPR.pdf
Pests of Blackgram, greengram, cowpea_Dr.UPR.pdf
 

Assessing Viewpoint Diversity in Search Results Using Ranking Fairness Metrics

  • 1. 1 WIS Web Information Systems Assessing Viewpoint Diversity in Search Results Using Ranking Fairness Metrics Tim Draws1, Nava Tintarev1, Ujwal Gadiraju1, Alessandro Bozzon1, and Benjamin Timmermans2 1TU Delft, The Netherlands 2IBM, The Netherlands t.a.draws@tudelft.nl
  • 2. 2 WIS Web Information Systems Biases in web search • Position bias2-4 • “Search Engine Manipulation Effect”1,5 How can we quantify (a lack of) viewpoint diversity in search results? Yes! Yes! Yes! Yes! Yes! No! No!
  • 3. 3 WIS Web Information Systems Ranking fairness metrics Statistical parity in fair ranking: protected attribute should not influence the ranking6 evaluate statistical parity for top i discount by rank normalize
  • 4. 4 WIS Web Information Systems Our paper RQ: Can ranking fairness metrics be used to assess viewpoint diversity in search results? Contributions: 1. Evaluation of existing metrics 2. Novel metric
  • 5. 7 WIS Web Information Systems Representing viewpoints Should we all be vegan? Strongly opposing Opposing Somewhat opposing Neutral Somewhat supporting Supporting Strongly supporting protected non-protected Binomial viewpoint fairness
  • 6. 8 WIS Web Information Systems Representing viewpoints Should we all be vegan? Strongly opposing Opposing Somewhat opposing Neutral Somewhat supporting Supporting Strongly supporting protected Multinomial viewpoint fairness
  • 7. 9 WIS Web Information Systems Metrics we consider Binomial viewpoint fairness – Normalized Discounted Difference (nDD)6 – Normalized Discounted Ratio (nDR)6 – Normalized Discounted Kullback-Leibler Divergence (nDKL)6 Multinomial viewpoint fairness – Normalized Discounted Jensen-Shannon Divergence (nDJS)
  • 8. 11 WIS Web Information Systems Simulation studies How do the metrics behave for different levels of viewpoint diversity? • Three synthetic data sets S1, S2, S3 • Per set created rankings to simulate different levels of viewpoint diversity
  • 9. 13 WIS Web Information Systems Weighted sampling procedure Rank Viewpoint 1 Strongly opposing 2 Strongly opposing 3 Opposing 4 Somewhat opposing 5 Supporting 6 Strongly opposing … … S1 sampling Per set: created rankings with different levels of ranking bias • Binomial viewpoint fairness: all opposing viewpoints get w1, all others w2 • Multinomial viewpoint fairness: random viewpoint get w1, all others w2
  • 10. 14 WIS Web Information Systems Results: binomial viewpoint fairness nDD nDR nDKL −1.0 −0.8 −0.6 −0.4 −0.2 0.0 0.2 0.4 0.6 0.8 1.0 −1.0 −0.8 −0.6 −0.4 −0.2 0.0 0.2 0.4 0.6 0.8 1.0 −1.0 −0.8 −0.6 −0.4 −0.2 0.0 0.2 0.4 0.6 0.8 1.0 0.0 0.1 0.2 0.3 0.4 0.5 0.6 0.7 0.8 0.9 1.0 Ranking bias Meanmetricvalue Distribution S1 S2 S3 • All metrics assess binomial viewpoint fairness (as expected) • All metrics are asymmetric (proportion of protected items and ”direction” of bias matter) • Which metric to use depends on strength of ranking bias
  • 11. 15 WIS Web Information Systems Results: multinomial viewpoint fairness 0.0 0.1 0.2 −1.0 −0.8 −0.6 −0.4 −0.2 0.0 0.2 0.4 0.6 0.8 1.0 Ranking bias MeannDJSvalue Distribution S1 S2 S3 • nDJS assesses multinomial viewpoint fairness • nDJS is also asymmetric (proportion of protected items and ”direction” of bias matter) • Careful interpretation: values not directly comparable to other metrics
  • 12. 16 WIS Web Information Systems Discussion • Metrics work for assessing viewpoint diversity • Considerations: – What is the underlying aim? – How balanced is the data overall? – How strong is the ranking bias? – What is the direction of ranking bias?
  • 13. 17 WIS Web Information Systems Take home and future work • Ranking fairness metrics can be used for assessing viewpoint diversity in search results – (when interpreted correctly) • Future work can use these metrics to… – …assess viewpoint diversity in real search results – …align different metric and behavioral outcomes
  • 14. 18 WIS Web Information Systems References [1] R. Epstein and R. E. Robertson. The search engine manipulation effect (SEME) and its possible impact on the outcomes of elections. Proceedings of the National Academy of Sciences of the United States of America, 112(33):E4512–E4521, 2015. [2] A. Ghose, P. G. Ipeirotis, and B. Li. Examining the impact of ranking on consumer behavior and search engine revenue. Management Science, 60(7):1632–1654, 2014. [3] L. A. Granka, T. Joachims, and G. Gay. Eye-tracking analysis of user behavior in WWW search. Proceedings of Sheffield SIGIR - Twenty-Seventh Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, pages 478–479, 2004. [4] B. Pan, H. Hembrooke, T. Joachims, L. Lorigo, G. Gay, and L. Granka. In Google we trust: Users’ decisions on rank, position, and relevance. Journal of Computer-Mediated Communication, 12(3):801– 823, 2007. [5] F. A. Pogacar, A. Ghenai, M. D. Smucker, and C. L. Clarke. The positive and negative influence of search results on people’s decisions about the efficacy of medical treatments. ICTIR 2017 - Proceedings of the 2017 ACM SIGIR International Conference on the Theory of Information Retrieval, pages 209– 216, 2017. [6] Yang, K., & Stoyanovich, J. Measuring fairness in ranked outputs. Proceedings of the 29th International Conference on Scientific and Statistical Database Management, pages 1-6, 2017.

Editor's Notes

  1. Introduce myself Second year PhD
  2. Search results on disputed topic: various viewpoints within topic diversity across ranking Position bias: trust and interact with higher results more Also voting preferences, judgment on medical treatment Important to maintain viewpoint diversity So far unclear how to assess viewpoint diversity in search results  this paper
  3. Protected non-protected attribute Example: gender bias in job candidate list Mostly: statistical parity Explain formula: F is function to evaluate statistical parity Low value (0) is fair, high value (1) is unfair How to use this for viewpoint diversity?
  4. Assess viewpoint div. using specific class of metrics: ranking fairness Simulation study on existing metrics Novel metric, also simulation study
  5. assumption: 7 classes Also assume that ranking assessor has specific aim as to what they are concerned about We consider two different aims
  6. assumption: 7 classes Also assume that ranking assessor has specific aim as to what they are concerned about We consider two different aims
  7. Quickly repeat formula, metrics differ in F F evaluates statistical parity by comparing to ideal ranking Briefly describe each metric nDJS because others are not applicable to multinomial (details in paper) These metrics QUANTIFY (no “fairness criterion”)
  8. Goal: see how metrics behave in different settings of viewpoint diversity Three data sets consisting of viewpoint labels Created rankings with different levels of ranking bias from each set Here: the more bias, the less viewpoint diversity Done by weighted sampling
  9. Goal: see how metrics behave in different settings of viewpoint diversity Three data sets consisting of viewpoint labels Created rankings with different levels of ranking bias from each set Here: the more bias, the less viewpoint diversity Done by weighted sampling
  10. Draw from data set without replacement Sampling is weighted Summary: two simulation studies, each with three sets, per set 21 settings of ranking bias, 1000 times per setting
  11. Draw from data set without replacement Sampling is weighted Two weights (which varies) to advantage / disadvantage Summary: two simulation studies, each with three sets, per set 21 settings of ranking bias, 1000 times per setting
  12. Explain ranking bias + mean metric outcome All metrics seem to work nDR is not normalized properly Whether to use nDD or nDKL depends on strength of ranking bias take home: use nDD / nDKL; proportion of protected + direction of bias is important to know
  13. Works Doesn’t go to 1 (don’t compare) Take home: same lessons as before
  14. Considerations need to be taken to decide which metric to use and how sensitive the metric is Considerations: Binomial or multinomial? The more balanced, the better the sensitivity If strong and binomial, use nDKL, otherwise nDD If protected group is advantaged, the same ranking bias produces a different outcome It would be good to have a simulator for interpreting metrics (I am working on that) In general, nDD, nDKL, or nDJS
  15. Correct interpretation: awareness of data skew and bias direction Future work: assessment + align metric outcomes with SEME