English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Automated decision systems (ADS) are increasingly used for consequentialdecision-making. These systems often rely on sophisticated yet opaque machinelearning models, which do not allow for understanding how a given decision wasarrived at. In this work, we conduct a human subject study to assess people'sperceptions of informational fairness (i.e., whether people think they aregiven adequate information on and explanation of the process and its outcomes)and trustworthiness of an underlying ADS when provided with varying types ofinformation about the system. More specifically, we instantiate an ADS in thearea of automated loan approval and generate different explanations that arecommonly used in the literature. We randomize the amount of information thatstudy participants get to see by providing certain groups of people with thesame explanations as others plus additional explanations. From our quantitativeanalyses, we observe that different amounts of information as well as people's(self-assessed) AI literacy significantly influence the perceived informationalfairness, which, in turn, positively relates to perceived trustworthiness ofthe ADS. A comprehensive analysis of qualitative feedback sheds light onpeople's desiderata for explanations, among which are (i) consistency (bothwith people's expectations and across different explanations), (ii) disclosureof monotonic relationships between features and outcome, and (iii)actionability of recommendations.

2022 acm conference on fairness, accountability, and transparency

"There Is Not Enough Information": On the Effects of Explanations on  Perceptions of Informational Fairness and Trustworthiness in Automated  Decision-Making