[Dbworld] CFP: WWW 2017 Workshop on Fairness, Accountability, and Transparency on the Web (FAT/WEB)

           ** Please forward to anyone who might be interested ** 
     --------------------------------------------------------------
 
  FAT/WEB: Workshop on Fairness, Accountability, and Transparency on the Web
                     https://fatweb.github.io/
 
            to be held on April 3-7, 2017, Perth, Australia
                     co-located with ACM WWW 2017
       --------------------------------------------------------------

IMPORTANT DATES:
================
Submission: 10 Feb 2017
Acceptance: 24 Feb 2017
Camera Ready: 10 Mar 2017
Workshop: 3 or 4 April 2017


ABSTRACT:
================
Recent academic and journalistic reviews of online web services have revealed that many systems exhibit subtle biases reflecting historic discrimination. Examples include racial and gender bias in search advertising, image recognition services, sharing economy mechanisms, pricing, and web-based delivery. The list of production systems exhibiting biases continues to grow and may be endemic to the way models are trained and the data used.

At the same time, concerns about user autonomy and fairness have been raised in the context of web-based experimentation such as A/B testing or explore/exploit algorithms. Given the ubiquity of this practice and increasing adoption in potentially-sensitive domains (e.g. health, employment), user consent and risk will become fundamental to the practice.

Finally, understanding the reasons behind predictions and outcomes of web services is important in optimizing a system and in building trust with users. However, it also has legal and ethical implications when the algorithm has an unintended or undesirable impact along social boundaries.
The objective of this full day workshop is to study and discuss the problems and solutions with algorithmic fairness, accountability, and transparency of models in the context of web-based services. 	


Topics:
================
We invite submissions dealing with issues of, 

¥ fairness: measuring and avoiding discrimination in web-based services, 

¥ accountability: auditing and proving socially-impactful properties of web-based services, and 

¥ transparency: communicating the logic behind decisions of web-based services with respect to methods (e.g. machine learning, experimentation, mechanism design) used in the domains of main WWW 2017 conference,

Computational Health
Crowdsourcing
Internet Monetization and Online Markets
Search
Security and Privacy
Semantics and Knowledge
Social Network Analysis and Computational Social Science
Systems and Infrastructure
Ubiquitous and Mobile Computing
User Modeling, Personalization and Experience
Web Mining and Content Analysis
Topics might include auditing a web-based recommender system for demographic bias, requesting informed consent for A/B tests that potentially put the user at risk, and explaining algorithmic decisions to users without putting the system at risk.

Paper Types:
================
Research in the area has begun to emerge in a variety of computer science subdisciplines. Work can be divided into four groups,

Case studies consisting of concentrated quantitative or qualitative analyses of systems for ethically problematic behavior.
Methods research studying quantitative approaches to defining and measuring fairness. This work includes topics such as formally defining metrics and rigorously auditing systems.
Tools designed to detect ethically problematic behavior. The majority of these methods use simulated users to conduct 'reverse A/B' tests on production systems. These tools often implement techniques developed in methods work and help produce novel case studies.
Remedies designed to avoid ethically problematic behavior. This work often adopts a metric developed in the methods work and designs an algorithm to balance, for example, fairness against revenue or accuracy.
We strongly encourage submissions from researchers outside of the computer science community.

Format:
================
Papers should be five page long with unlimited citations using the ACM SIG Proceedings template. Reviewing will be double-blind. Authors should anonymize their paper before submission.

Submission:
================
The conference reviewing system can be found at https://easychair.org/conferences/?conf=fatweb2017.

Accepted submissions will be made available to attendees but will not be published in an archival format.
   
Chairs:
================
Fernando Diaz, Microsoft Research, USA 
Sara Hajian, Eurecat, Technology Center of Catalonia, Spain
Maarten de Rijke , University of Amsterdam, Netherlands


Program Committee:
================
Solon Barocas, Microsoft Research, USA
Bettina Berendt, KU Leuven, Belgium
Joanna J Bryson, University of Bath, USA
Hal Daume, University of Maryland College Park, USA
Josep Doming-Ferrer, Universitat Rovira i Virgili, Spain
Sorelle Friedler, Haverford College, USA
Krishna Gummadi, MPI-SWS, Germany
Anna Lauren Hoffmann, University of California, Berkeley
Dirk Hovy, University of Copenhagen, Denmark
Toshihiro Kamishima, National Institute of Advanced Industrial Science and Technology, Japan
Joshua Kroll, CloudFlare, USA
Kristian Lum, Human Rights Data Analysis Group, USA
Alexandra Olteanu, Ecole Polytechnique Federale de Lausanne, Switzerland
Shannon L. Spruit, Delft University, Netherlands
Julia Stoyanovich, Drexel University, USA
Suresh Venkatasubramanian, University of Utah, USA
Christo Wilson, Northeastern University, USA
 



_______________________________________________
Please do not post msgs that are not relevant to the database community at large.  Go to www.cs.wisc.edu/dbworld for guidelines and posting forms.
To unsubscribe, go to https://lists.cs.wisc.edu/mailman/listinfo/dbworld