Designing and Building Evidence-Based Intelligent Algorithmic Systems in Online Communities

2019-12
Loading...
Thumbnail Image

Persistent link to this item

Statistics
View Statistics

Journal Title

Journal ISSN

Volume Title

Title

Designing and Building Evidence-Based Intelligent Algorithmic Systems in Online Communities

Alternative title

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.