Dissertation/Thesis Abstract

The Mining and Application of Diverse Cultural Perspectives in User-Generated Content
by Hecht, Brent Jaron, Ph.D., Northwestern University, 2013, 421; 3556613
Abstract (Summary)

Wikipedia articles, tweets, and other forms of user-generated content (UGC) play an essential role in the experience of the average Web user. Outside the public eye, UGC has become equally indispensable as a source of world knowledge for systems and algorithms that help us make sense of big data. In this thesis, we demonstrate that UGC reflects the cultural diversity of its contributors to a previously unidentified extent, and that this diversity has important implications for Web users and existing UGC-based technologies. Focusing on Wikipedia, Flickr, and Twitter, we show how UGC diversity can be extracted and measured using techniques from artificial intelligence and geographic information science. Finally, through two novel applications—Omnipedia and Atlasify—we highlight the exciting potential for a new class of technologies enabled by the ability to harvest diverse perspectives from UGC.

Indexing (document details)
Advisor: Gergle, Darren
Commitee: Adar, Eytan, Downey, Doug, Horn, Mike
School: Northwestern University
Department: Computer Science
School Location: United States -- Illinois
Source: DAI-B 74/07(E), Dissertation Abstracts International
Subjects: Computer science
Keywords: Geography, Multilingual, Semantic relatedness, User-generated content, Wikipedia
Publication Number: 3556613
ISBN: 9781267988539
Copyright © 2019 ProQuest LLC. All rights reserved. Terms and Conditions Privacy Policy Cookie Policy