Ranking algorithms can reinforce inequalities in social networks


Feb 10, 2022

The way people connect on Twitter or in Academia can distort and influence the visibility and ranking of minorities, and algorithms amplify these biases, according to a Hub study

 

Online social networks claim to make connections and bring people together. But their ranking and recommender algorithms – which suggest people whom to connect with, or who the most relevant scientists in a particular field are – can, in fact, exacerbate inequalities by discriminating against certain groups of people in top ranks, a Hub study has found.

 

The study, published in Scientific Reports, investigated how social mechanisms influence the rank distributions of two well-known algorithms, PageRank – one of the main algorithms on which Google’s search engine is built – and Who-to-Follow, Twitter’s algorithm which suggests people you aren’t currently following that you may find interesting.

 

“The findings suggest that ranking and recommender algorithms in online social networks such as Twitter can distort the visibility of minorities in unexpected ways,” says one of the authors of the paper, Fariba Karimi, who leads the team at the Hub working on Network Inequality.

 

Understanding algorithms

 

“It has been shown that ranking algorithms tend to increase the popularity of users that are already popular and that can lead to loss of opportunities for certain groups of people,” explains Lisette Espín-Noboa, a PostDoc at the Hub and first author of the paper. “We wanted to understand when these algorithms can go wrong” depending on the structure and characteristics of a network, according to Lisette.

 

In the study, Lisette and her team simulated different networks, composed of 2,000 people [avatars? “agents”?], and adjusted the social mechanisms of relationships between individuals in each. They were able to make variations in the properties assigned to each network, including the proportion of the minority, how active users were in connecting with other users, and the way people connected in the network – specifically, whether individuals associated with others who were already popular, and if members tended to link with those who were similar to them, a principle social scientists call homophily.

 

Main social mechanism

 

The researchers found out the main social mechanism responsible for distorting the visibility of minorities in rankings was homophily together with the proportion of the minority. When the majority group associated mostly with other members of the majority, the minority group was underrepresented in top ranks, explains Lisette.

 

“However, minorities can overcome this underrepresentation by connecting strategically with others and can try to achieve at least statistical parity in top ranks,” says Lisette.

 

“Statistical parity means that if the minority represents 20 percent of people in the network, then the same ratio should be reflected in each top-k of the rank. Then, one way to increase the visibility of minorities in the rank is by making the minorities more active in the network. That is, minorities should create more connections to others,” points out Lisette. Another way is by diversifying the connections of the majority, by creating more connections from the majority group to the minority group.

 

More realistic scenarios

 

“We have seen in an earlier paper how homophily can influence the ranking of minorities. The difference is that Lisette’s paper assumes more realistic social network scenarios and is looking not only at ranking algorithms but also social recommender algorithms that social network platforms such as Twitter uses,” concludes Fariba.

 

 

The paper Inequality and inequity in network-based ranking and recommendation algorithms, whose other co-authors are CSH External Faculty members Claudia Wagner and Markus Strohmaier just appeared in Scientific Reports.

 


Publication

W. Schueller, J. Wachs, V. D. P. Servedio, S. Thurner, V. Loreto

Evolving collaboration, dependencies, and use in the Rust Open Source Software ecosystem

Scientific Data 9 (2022) 703

Press

Staatsanwälte jagen mit Datenforschern Cyberkriminelle [feat.Bernhard Haslhofer]


Salzburger Nachrichten, Jan 27, 2023

Spotlight

Jan 20, 2023

CSH-STATEMENT | New methods for investigating child pornography

Press

Studie: Berlin könnte erheblichen Teil seines Gemüsebedarfs [feat.Diego Rybski]


Stern, Jan 27, 2023

Publication

N. Pontika, T. Klebel, A. Correia, H. Metzler, P. Knoth, T. Ross-Hellauer

Indicators of research quality, quantity, openness and responsibility in institutional review, promotion and tenure policies across seven countries

Quantitative Science Studies 1-49

Event

Workshop für Journalist:innen: "Put a Piece of Science in your Story"


Mar 03, 2023 | 15:0017:00

Complexity Science Hub Vienna

Research News

Jan 24, 2023

Berlin could produce more than 80% of its fresh vegetables locally

News

Feb 2, 2023

Cybercrime is increasing rapidly, new methods are ready

Event

CSH Talk by José Moran: "Dynamics of (auto)correlated firms"


Feb 24, 2023 | 15:0016:00

Complexity Science Hub Vienna

Event

CSH Talk by Ambra Amico: "Structure and resilience of large-scale distribution networks: a complex system perspective to supply-chains"


Mar 03, 2023 | 15:0016:00

Complexity Science Hub Vienna

Press

Warum in der Welt doch Chaos herrscht [feat.J.Doyne Farmer]


Wiener Zeitung, Jan 28, 2023

Publication

V.D.P. Servedio, M. R. Ferreira, N. Reisz, R. Costas, S. Thurner

Scale-free growth in regional scientific capacity building explains long-term scientific dominance

Chaos, Solitons & Fractals 167 (2023) 113020

Publication

W. Schueller, J. Wachs, V. D. P. Servedio, S. Thurner, V. Loreto

Evolving collaboration, dependencies, and use in the Rust Open Source Software ecosystem

Scientific Data 9 (2022) 703

Press

Staatsanwälte jagen mit Datenforschern Cyberkriminelle [feat.Bernhard Haslhofer]


Salzburger Nachrichten, Jan 27, 2023

Spotlight

Jan 20, 2023

CSH-STATEMENT | New methods for investigating child pornography

Press

Studie: Berlin könnte erheblichen Teil seines Gemüsebedarfs [feat.Diego Rybski]


Stern, Jan 27, 2023

Publication

N. Pontika, T. Klebel, A. Correia, H. Metzler, P. Knoth, T. Ross-Hellauer

Indicators of research quality, quantity, openness and responsibility in institutional review, promotion and tenure policies across seven countries

Quantitative Science Studies 1-49

Event

Workshop für Journalist:innen: "Put a Piece of Science in your Story"


Mar 03, 2023 | 15:0017:00

Complexity Science Hub Vienna

Research News

Jan 24, 2023

Berlin could produce more than 80% of its fresh vegetables locally

News

Feb 2, 2023

Cybercrime is increasing rapidly, new methods are ready

Event

CSH Talk by José Moran: "Dynamics of (auto)correlated firms"


Feb 24, 2023 | 15:0016:00

Complexity Science Hub Vienna

Event

CSH Talk by Ambra Amico: "Structure and resilience of large-scale distribution networks: a complex system perspective to supply-chains"


Mar 03, 2023 | 15:0016:00

Complexity Science Hub Vienna

Press

Warum in der Welt doch Chaos herrscht [feat.J.Doyne Farmer]


Wiener Zeitung, Jan 28, 2023

Publication

V.D.P. Servedio, M. R. Ferreira, N. Reisz, R. Costas, S. Thurner

Scale-free growth in regional scientific capacity building explains long-term scientific dominance

Chaos, Solitons & Fractals 167 (2023) 113020

News

Feb 2, 2023

Cybercrime is increasing rapidly, new methods are ready

Research News

Jan 24, 2023

Berlin could produce more than 80% of its fresh vegetables locally

Spotlight

Jan 20, 2023

CSH-STATEMENT | New methods for investigating child pornography

Research News

Jan 23, 2023

Predicting human group sizes with physics

Research News

Jan 19, 2023

Simply explained: Decentralized Finance, Blockchains and smart contracts

News

Jan 16, 2023

CSH Winter School is off to a great start

Spotlight

Jan 11, 2023

Explore the world's supply chains

Research News

Jan 3, 2023

Diabetes mellitus: Women are at higher risk of venous thromboembolism than men

Research News

Dec 28, 2022

NO CRITICAL MASS OF SCIENTISTS: TRY TO BE A PIONEER

Research News

Dec 19, 2022

Of mice and men

Research News

Dec 14, 2022

Tweets can prevent suicides

Press

Algorithmen lernen zu diskriminieren [feat. Fariba Karimi]


Die Presse, Jan 28, 2023

Press

Warum in der Welt doch Chaos herrscht [feat.J.Doyne Farmer]


Wiener Zeitung, Jan 28, 2023

Press

Studie: Berlin könnte erheblichen Teil seines Gemüsebedarfs [feat.Diego Rybski]


Stern, Jan 27, 2023

Press

Staatsanwälte jagen mit Datenforschern Cyberkriminelle [feat.Bernhard Haslhofer]


Salzburger Nachrichten, Jan 27, 2023

Press

Totes Netz [feat.Christian Diem]


Ö1 Dimensionen, Jan 24, 2023

Press

Arzneimittelengpass in Österreich [feat.Peter Klimek]


Ö1 / Morgenjournal, Jan 24, 2023

Press

Stoppt den Kindesmissbrauch [feat.Bernhard Haslhofer]


ORF 2 / Thema, Jan 24, 2023

Press

Menschen verhalten sich wie Teilchen mit Spin [feat.Stefan Thurner, Jan Korbel]


APA-Science, Jan 23, 2023

Press

Wie der Kreml geflohene Russen drangsaliert [feat.Johannes Wachs]


Handelsblatt, Jan 20, 2023

Press

So machen wir den Markt kaputt [feat.Stefan Thurner]


Die Presse, Jan 8, 2023

Publication

V.D.P. Servedio, M. R. Ferreira, N. Reisz, R. Costas, S. Thurner

Scale-free growth in regional scientific capacity building explains long-term scientific dominance

Chaos, Solitons & Fractals 167 (2023) 113020

Publication

M. Leutner, M. Butylina, C. Matzhold, et al.

Simvastatin therapy in higher dosages deteriorates bone quality: Consistent evidence from population-wide patient data and interventional mouse studies

Biomedicine & Pharmacotherapy 158 (2023) 114089

Publication

W. Schueller, J. Wachs, V. D. P. Servedio, S. Thurner, V. Loreto

Evolving collaboration, dependencies, and use in the Rust Open Source Software ecosystem

Scientific Data 9 (2022) 703

Publication

N. Pontika, T. Klebel, A. Correia, H. Metzler, P. Knoth, T. Ross-Hellauer

Indicators of research quality, quantity, openness and responsibility in institutional review, promotion and tenure policies across seven countries

Quantitative Science Studies 1-49

Publication

H. Kong, S. Martin-Gutierrez, F. Karimi

Influence of the first-mover advantage on the gender disparities in physics citations

Communications Physics 5 (243) (2022)

Publication

A. Pichler, M. Pangallo, M. del Rio-Chanona, F. Lafond, D. Farmer

Forecasting the propagation of pandemic shocks with a dynamic input-output model

Journal of Economic Dynamics and Control (2022) 104527

Publication

J. Lasser, S. Taofeek Aroyehun, et al.

Social media sharing of low quality news sources by political elites

PNAS Nexus (2022) pgac186

Publication

R. Prieto Curiel, A. Schumann, I. Heo, P. Heinrigs

Detecting cities with high intermediacy in the African urban network

Computers, Environment and Urban Systems 98 (2022) 101869

Publication

T. Reisch, G. Heiler, C. Diem, P. Klimek, S. Thurner

Monitoring supply networks from mobile phone data for estimating the systemic risk of an economy

Scientific Reports 12 (13347) (2022)

Publication

G. De Marzo, F. Pandolfelli, V.D.P. Servedio

Modeling innovation in the cryptocurrency ecosystem

Scientific Reports 12 (12942) (2022)

Publication

A. Nerpel, et al.

SARS-ANI: a global open access dataset of reported SARS-CoV-2 events in animals

Scientific Data 9 (438) (2022)

Publication

M. Kaleta, J. Lasser, E. Dervic, et al.

Stress-testing the resilience of the Austrian healthcare system using agent-based simulation

Nature Communications 13 (4259) (2022)

Event

CSH Talk by José Moran: "Dynamics of (auto)correlated firms"


Feb 24, 2023 | 15:0016:00

Complexity Science Hub Vienna

Event

Workshop für Journalist:innen: "Put a Piece of Science in your Story"


Mar 03, 2023 | 15:0017:00

Complexity Science Hub Vienna

Event

CSH Talk by Ambra Amico: "Structure and resilience of large-scale distribution networks: a complex system perspective to supply-chains"


Mar 03, 2023 | 15:0016:00

Complexity Science Hub Vienna

Event

CSH Talk by Gašper Tkačik: "Statistical analysis and optimality of biological systems"


Feb 17, 2023 | 14:0015:00

Complexity Science Hub Vienna

Event

CSH Talk by Nicolò Vallarano:"An Agent-based model of Ethereum Proof-of-Stake consensus"


Feb 10, 2023 | 15:0016:00

Complexity Science Hub Vienna

Event

CSH Workshop: "Monitoring Social Stress: a data-driven approach to understanding 'polycrisis”


Feb 07, 2023Feb 08, 2023

Complexity Science Hub Vienna