Modeling Human Learning of Data Quality Rules

Graduate Thesis Or Dissertation

Public Deposited

Citeable URL: https://ir.library.oregonstate.edu/concern/graduate_thesis_or_dissertations/41687r04s

Descriptions

Attribute Name	Values
Creator	Habibelahian, Omeed A.
Abstract	The process of cleaning data is quite laborious and can be complicated by the presence of inconsistencies and other issues in the data, leading many data scientists to utilize interactive data cleaning software. However, many current state-of-the-art cleaning solutions fail to account for the reality that the human needs to explore the data to learn and as a result may periodically provide noisy feedback. Therefore, we need to understand how humans fundamentally learn data quality rules over the data and how that translates to identifying violations of these rules in the data they work with. In this thesis, we perform an empirical analysis of how humans understand and iteratively learn data quality rules, working to both quantify and model this learning process. We find that a Bayesian learning model replicates user behavior well when the model success definition is strict, while a hypothesis testing model also performs well when the success definition is loosened.
License	All rights reserved
Resource Type	Masters Thesis
Date Issued	2021-06-07
Degree Level	Master's
Degree Name	Master of Science (M.S.)
Degree Field	Computer Science
Degree Grantor	Oregon State University
Commencement Year	2021
Advisor	Termehchy, Arash
Committee Member	Park, Si Hong Wong, Weng-Keen Kahng, Minsuk
Academic Affiliation	Electrical Engineering and Computer Science
Rights Statement	In Copyright
Publisher	Oregon State University
Peer Reviewed	No
Language	English [eng]

Parents:

This work has no parents.

In Collection:

Thumbnail	Title	Date Uploaded	Visibility	Actions
	HabibelahianOmeedA2021.pdf	2021-06-10	Public	Download