Cornell University
Library
Cornell UniversityLibrary

eCommons

Help
Log In(current)
  1. Home
  2. Cornell University Graduate School
  3. Cornell Theses and Dissertations
  4. Intentions and Perceptions in Technology-Mediated Communication

Intentions and Perceptions in Technology-Mediated Communication

File(s)
Fu_cornellgrad_0058F_12920.pdf (2.9 MB)
Permanent Link(s)
https://doi.org/10.7298/gcpz-0q52
https://hdl.handle.net/1813/111705
Collections
Cornell Theses and Dissertations
Author
Fu, Liye
Abstract

Technological developments have greatly enhanced our communication experience. We are now presented with unprecedented opportunities to interact with people from different backgrounds in a wide range of settings. However, these new communication opportunities also present new challenges for the interlocutors. This dissertation aims to analyze these challenges and explore opportunities to develop systems to help interlocutors navigate the increasingly diverse communication circumstances more easily. We start by highlighting two sources of diversity in technology-mediated communication and the challenges they bring. First, the use of technology to mediate communication has introduced an additional layer of variability. Since different mediating channels can offer different affordances and apply different transformations to messages, we might not always have the right expectations for the particular channel we are using. Using machine-translated communication as an example, we demonstrate how Natural Language Processing (NLP) techniques can be used to assess the input-output behaviors of the communication channels systematically. Second, technology-mediated communication has allowed us to connect with a more diverse pool of interlocutors. As we are more likely to communicate with people whose assumptions and perspectives differ from ours, we might not always perceive our interlocutors' intentions accurately or have our intentions correctly perceived. To prevent or reduce such misalignment of intentions and perceptions, we explore possible sources of misunderstandings and the types of information needed to help address them. We then demonstrate how we could move towards more circumstance-sensitive communication assistance by incorporating relevant circumstantial information. In particular, we introduce an example system that aims to facilitate the accurate communication of politeness by suggesting paraphrases, taking both the properties of the communication channel and characteristics of the interlocutors into account. We further discuss other potential forms of communication assistance systems and end with considerations for the responsible design of such systems.

Description
134 pages
Date Issued
2022-05
Keywords
AI-Mediated Communication
•
Natural Language Processing
•
Technology-Mediated Communication
Committee Chair
Danescu-Niculescu-Mizil, Cristian
Committee Member
Lee, Lillian
Kleinberg, Jon M.
Degree Discipline
Computer Science
Degree Name
Ph. D., Computer Science
Degree Level
Doctor of Philosophy
Rights
Attribution 4.0 International
Rights URI
https://creativecommons.org/licenses/by/4.0/
Type
dissertation or thesis
Link(s) to Catalog Record
https://newcatalog.library.cornell.edu/catalog/15529943

Site Statistics | Help

About eCommons | Policies | Terms of use | Contact Us

copyright © 2002-2026 Cornell University Library | Privacy | Web Accessibility Assistance