Designing and Building Evidence-Based Intelligent Algorithmic Systems in Online Communities
2019-12
Loading...
View/Download File
Persistent link to this item
Statistics
View StatisticsJournal Title
Journal ISSN
Volume Title
Title
Designing and Building Evidence-Based Intelligent Algorithmic Systems in Online Communities
Alternative title
Authors
Published Date
2019-12
Publisher
Type
Thesis or Dissertation
Abstract
Online communities, such as social networks and peer production communities, are an essential part of our daily life. They act as an information system for various purposes and have drawn the attention of research from multiple disciplines. One thread of research studies online communities through the lens of social science theories to understand community insights for design implications. Another thread of research involves the development and support of artificial intelligence that is used to build and integrate algorithmic technologies into online communities to assist humans with various tasks. However, a series of challenges and issues have been discussed in building those intelligent systems, such as lack of understanding of community social dynamics and stakeholders’ values, and lack of transparency of trade-offs in algorithm design. In addressing these challenges, my dissertation connects these two threads of research. It takes human-centered approaches by conducting analytical studies through the lens of social science. These studies guide the building of effective intelligent algorithmic systems in online communities and inform the design of interactive interfaces that communicate algorithm trade-offs to stakeholders who lack technical backgrounds in order to support their decision making. My dissertation contributes to the ongoing conversations about AI system building for online communities at a large scale and about participatory design of machine learning systems with lay people.
Description
University of Minnesota Ph.D. dissertation.December 2019. Major: Computer Science. Advisors: Haiyi Zhu, Loren Terveen. 1 computer file (PDF); x, 142 pages.
Related to
Replaces
License
Collections
Series/Report Number
Funding information
Isbn identifier
Doi identifier
Previously Published Citation
Other identifiers
Suggested citation
Yu, Bowen. (2019). Designing and Building Evidence-Based Intelligent Algorithmic Systems in Online Communities. Retrieved from the University Digital Conservancy, https://hdl.handle.net/11299/213101.
Content distributed via the University Digital Conservancy may be subject to additional license and use restrictions applied by the depositor. By using these files, users agree to the Terms of Use. Materials in the UDC may contain content that is disturbing and/or harmful. For more information, please see our statement on harmful content in digital repositories.