Show simple item record

dc.contributor.supervisorBunt, Andrea (Computer Science)en_US
dc.contributor.authorAnik, Md Ariful Islam
dc.date.accessioned2021-01-15T19:52:30Z
dc.date.available2021-01-15T19:52:30Z
dc.date.copyright2020-11-25
dc.date.issued2020-11en_US
dc.date.submitted2020-11-25T18:55:34Zen_US
dc.identifier.urihttp://hdl.handle.net/1993/35244
dc.description.abstractTraining datasets fundamentally impact the performance of machine learning systems. Any biases introduced during training (implicit or explicit) are often reflected in the system’s behaviors leading to questions about fairness and loss of trust in the system. Yet, information on training data is rarely communicated to the stakeholders. In this thesis, I explore the concept of data-centric explanations for machine learning systems that describe the training data to end-users. I design data-centric explanations that focus on providing information on training data. Through a formative study, I investigate the potential utility of such an approach and the data-centric information that users find most compelling. In a second study, I investigate reactions to the explanations across four different system scenarios. The results show that data-centric explanations can impact how users judge the trustworthiness of a system and can assist users in assessing fairness. I discuss the implications of the findings for designing explanations to support users’ perception of machine learning systems.en_US
dc.language.isoengen_US
dc.rightsinfo:eu-repo/semantics/openAccess
dc.subjectMachine Learning Systemsen_US
dc.subjectExplanationsen_US
dc.subjectTraining Dataen_US
dc.subjectTransparencyen_US
dc.titleData-centric explanations: Explaining training data of machine learning systems to promote transparencyen_US
dc.typeinfo:eu-repo/semantics/masterThesis
dc.typemaster thesisen_US
dc.degree.disciplineComputer Scienceen_US
dc.contributor.examiningcommitteeLeung, Carson (Computer Science) Wang, Yang (Computer Science)en_US
dc.degree.levelMaster of Science (M.Sc.)en_US
dc.description.noteFebruary 2021en_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record