eCommons

 

Intentions and Perceptions in Technology-Mediated Communication

Other Titles

Author(s)

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.

Journal / Series

Volume & Issue

Description

134 pages

Sponsorship

Date Issued

2022-05

Publisher

Keywords

AI-Mediated Communication; Natural Language Processing; Technology-Mediated Communication

Location

Effective Date

Expiration Date

Sector

Employer

Union

Union Local

NAICS

Number of Workers

Committee Chair

Danescu-Niculescu-Mizil, Cristian

Committee Co-Chair

Committee Member

Lee, Lillian
Kleinberg, Jon M.

Degree Discipline

Computer Science

Degree Name

Ph. D., Computer Science

Degree Level

Doctor of Philosophy

Related Version

Related DOI

Related To

Related Part

Based on Related Item

Has Other Format(s)

Part of Related Item

Related To

Related Publication(s)

Link(s) to Related Publication(s)

References

Link(s) to Reference(s)

Previously Published As

Government Document

ISBN

ISMN

ISSN

Other Identifiers

Rights

Attribution 4.0 International

Types

dissertation or thesis

Accessibility Feature

Accessibility Hazard

Accessibility Summary

Link(s) to Catalog Record