Coronavirus Update 16:03:2020; EVENT POSTPONED: With the rapidly changing situation with respect to the spread of COVID-19, we have been following the local advice of the university specifically relating to travel and organised gatherings of people. This advice is now that whenever possible events should be postponed and the university has moved to online teaching and meetings from today.

Therefore, and to help to contain the spread of COVID-19, we reached the conclusion that the safest option is to postpone the workshop until later in the year when the situation has been contained.

Fairness and Bias in Information Retrieval is a one-day workshop that will be held at the University of Glasgow on 27th March. The workshop will bring together practitioners from academia and industry to discuss the challenges relating to fairness in information retrieval (IR) that are faced by industry, and the recent advances in fair IR research.

Many organisations are bound by regulations or laws that require them to ensure fairness in the information that they provide to the public. For example, media companies should be impartial in the on-line content that they produce to comply with editorial guidelines, and governments must be unbiased when releasing or retaining information through FOI and GDPR. IR systems are playing an increasingly important role in selecting the information to be made available to the public in contexts such as these, e.g. search and recommendation systems for finding on-line content or technology-assisted review for identifying sensitive government information.

The objective of the workshop is to raise awareness of fair IR challenges, to foster knowledge transfer and encourage discussion with a view to identifying new research directions in fair IR systems.

Speakers:

Maarten De Rijke, University of Amsterdam, The Netherlands.

Jean-Michel Renders, Naver Labs Europe, France.

Rishabh Mehrotra, Spotify, London, UK.

Carlos Castillo, Universitat Pompeu Fabra, Spain

Leif Azzopardi, University of Strathclyde, UK.

Adam Harland, BBC, UK

Pablo Castells, Universidad Autónonoma de Madrid, Spain.

Claudia Hauff, Delft University of Technology (TU Delft), The Netherlands.

Tim Gollins, National Records of Scotland, UK.

Tameem Adel, University of Glasgow, UK.

Frank Hopfgartner, University of Sheffield, UK.

If you would like to contribut a presentation or poster to be included in the days activities, please contact Graham, graham.mcdonald@glasgow.ac.uk

Location:

Business School Lecture Theatre, Main Building Room 206

University of Glasgow, Glasgow, G12 8QQ.

Agenda:

08:30 - 09:00 Coffee

09:00 - 09:10 Introduction and Welcome

Chair: TBC

09:10 - 09:55 Maarten De Rijke, Actionable Interpretability

09:55 - 10:25 Leif Azzopardi, The Fairness Hypothesis: Is fairer, better?

10:25 - 10:45 Frank Hopfgartner, Promoting Algorithmic Transparency in Information Access

10:45 - 11:00 Coffee

Chair: TBC

11:00 - 11:45 Carlos Castillo, Fairness in Ranking

11:45 - 12:05 Tameem Adel, One-network Adversarial Fairness

12:05 - 12:30 Claudia Hauff, SIREN: A Simulation Framework for Understanding the Effects of Recommender Systems in Online News Environments

12:30 - 12:50 Pablo Castells, Bias in recommendation: avoid it or embrace it?

12:55 - 13:45 Lunch

Chair: TBC

13:45 - 14:15 Rishabh Mehrotra, Diversity & Fairness in multi-stakeholder Marketplaces

14:15 - 14:45 Adam Harland, Developing recommendation engines in a public service organisation

14:45 - 15:05 Tim Gollins, The Challenges of Fair Retrieval in Archives and the Public Sector

15:05 - 15:20 Coffee

Chair

15:20 - 16:05 Jean-Michel Renders, Robin Hood in the age of AI: efficient and scalable Fair Ranking based on Majorization Theory

16:05 - 16:45 Breakout Groups Discussions

16:45 - 17:30 Breakout Groups Reporting

17:30 - 17:40 Closing Remarks

18:00 Pub!!

This event is sponsered by: