Section: New Results

Transparency and Bias

In this last set of results, we investigate transparency and bias in data management.

Bias in online information has recently become a pressing issue, with search engines, social networks and recommendation services being accused of exhibiting some form of bias. In [15], we make the case for a systematic approach towards measuring bias. To this end, we discuss formal measures for quantifying the various types of bias, we outline the system components necessary for realizing them, and we highlight the related research challenges and open problems.

In [19], we pursue an investigation of data-driven collaborative work-flows. In the model, peers can access and update local data, causing side-effects on other peers' data. In this paper, we study means of explaining to a peer her local view of a global run, both at runtime and statically. We consider the notion of “scenario for a given peer” that is a subrun observationally equivalent to the original run for that peer. Because such a scenario can sometimes differ significantly from what happens in the actual run, thus providing a misleading explanation , we introduce and study a faithfulness requirement that ensures closer adherence to the global run. We show that there is a unique minimal faithful scenario, that explains what is happening in the global run by extracting only the portion relevant to the peer. With regard to static explanations, we consider the problem of synthesizing, for each peer, a “view program” whose runs generate exactly the peer's observations of the global runs. Assuming some conditions desirable in their own right, namely transparency and boundedness, we show that such a view program exists and can be synthesized. As an added benefit, the view program rules provide provenance information for the updates observed by the peer.

Finally, in two articles oriented towards applications and policy, we discuss bias and neutrality and their impact on regulation. In [18] we discuss the different forms of neutrality in the digital world, from the neutrality of networks to neutrality of content. In [17], we investigate the impact of bias and neutrality concerns on algorithms used by businesses.