Link to the University of Pittsburgh Homepage
Link to the University Library System Homepage Link to the Contact Us Form

Data Reliability Assessment based on subjective opinions

Zhang, Danchen (2021) Data Reliability Assessment based on subjective opinions. Doctoral Dissertation, University of Pittsburgh. (Unpublished)

This is the latest version of this item.

Download (3MB) | Preview


In the big data era, numerous data fluctuates society and people's life. These data come from diverse sources, and various information can be inferred and extracted. However, data quality usually cannot be guaranteed, and hence decision making with such unreliable data may lead to considerable losses. Accurate data reliability assessment mechanisms can help recognize the distrustful information and then filter unreliable data out.

In this work, I consider a novel approach to assess data reliability based on subjective opinions. I structure the data propagation model in terms of data sources producing and evaluating different statements. Next, I explore data history labels, value conflicts, and uncertainty. For different combinations of those parameters, I consider common scenarios, including handling fake news, truth discovery, data cleaning, as well as discovering cancer-driving genes.

In my dissertation, I explore how to accurately assess data reliability and how to make a decision based on evaluated reliability. I propose a series of subjective opinion based models to assess each scenario's reliability and compare them with state-of-art models through experiments on real-world data.


Social Networking:
Share |


Item Type: University of Pittsburgh ETD
Status: Unpublished
CreatorsEmailPitt UsernameORCID
Zhang, Danchendaz45@pitt.eduDAZ450000-0002-0274-3997
ETD Committee:
TitleMemberEmail AddressPitt UsernameORCID
Committee ChairZadorozhny, Vladimirviz@pitt.eduviz
Committee MemberHe, DaqingDAH44@pitt.edudah44
Committee MemberOleshchuk,
Committee MemberPelechrinis, Kostaskpele@pitt.edukpele
Date: 7 June 2021
Date Type: Publication
Defense Date: 18 March 2021
Approval Date: 7 June 2021
Submission Date: 26 April 2021
Access Restriction: No restriction; Release the ETD for access worldwide immediately.
Number of Pages: 101
Institution: University of Pittsburgh
Schools and Programs: School of Computing and Information > Information Science
Degree: PhD - Doctor of Philosophy
Thesis Type: Doctoral Dissertation
Refereed: Yes
Uncontrolled Keywords: Data reliability assessment, machine learning, fake news detection, truth discovery, cancer driver gene discovery
Date Deposited: 07 Jun 2021 20:49
Last Modified: 07 Jun 2021 20:49

Available Versions of this Item


Monthly Views for the past 3 years

Plum Analytics

Actions (login required)

View Item View Item