Capturing Bias: Diversity-aware Computation for Accurate Big Media Data Analysis
This project focuses on achieving reliable and explainable big data analysis of media files. In particular, metrics will be developed that indicate how accurate the results of the big data analysis are.
In this process, use is made, among other things, of crowd-sourcing the opinions of citizens. Whereas in the previous project the emphasis is on achieving fairness, here the emphasis is on quantifying the degree of accuracy, relationship to other values such as diversity and then visualising the resulting complexity of decision-making in media analysis.
In the project, computer scientists, media scientists and administrators from the VU, Utrecht University, Leiden University and Delft University of Technology work together with the Institute for Sound and Vision on use cases and technical demonstrations. In this way, the project not only aims to make scientific progress, but also to offer action perspectives for new forms of presentation and communication about the results of big data analysis techniques.
This call is closed
The projects have been awarded, at the bottom of this page the current projects.
Sign up for our newsletter and stay informed of the latest news Commit2data
View the projects related to the theme VWData