Identity Signals in Emoji do not Influence Perception of Factual Truth on Twitter

Alexander Robertson; Walid Magdy; Sharon Goldwater

doi:10.36190/2021.06

Identity Signals in Emoji do not Influence Perception of Factual Truth on Twitter

Alexander Robertson, Walid Magdy, Sharon Goldwater

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

Prior work has shown that Twitter users use skin-toned emoji as an act of self-representation to express their racial/ethnic identity. We test whether this signal of identity can influence readers’ perceptions about the content of a post containing that signal. In a large scale (n=944) pre-registered controlled experiment, we manipulate the presence of skin-toned emoji and profile photos in a task where readers rate obscure trivia facts (presented as tweets) as true or false. Using a Bayesian statistical analysis, we find that neither emoji nor profile photo has an effect on how readers rate these facts. This result will be of some comfort to anyone concerned about the manipulation of online users through the crafting of fake profiles.

Original language	English
Title of host publication	Workshop Proceedings of the 15th International AAAI Conference on Web and Social Media
Publisher	AAAI Press
Number of pages	5
DOIs	https://doi.org/10.36190/2021.06
Publication status	Published - 1 Jun 2021
Event	4th International Workshop on Emoji Understanding and Applications in Social Media - Online Duration: 7 Jun 2021 → 7 Jun 2021 http://emoji2021.aiisc.ai/

Workshop

Workshop	4th International Workshop on Emoji Understanding and Applications in Social Media
Abbreviated title	Emoji 2021
Period	7/06/21 → 7/06/21
Internet address	http://emoji2021.aiisc.ai/

Access to Document

10.36190/2021.06Licence: All Rights Reserved

Identity Signals_ROBERTSON_DOA30042021_AFVAccepted author manuscript, 265 KBLicence: All Rights Reserved

http://workshop-proceedings.icwsm.org/abstract?id=2021_06Licence: All Rights Reserved

Cite this

@inproceedings{25df6803236f48e78fbaa623ff241995,

title = "Identity Signals in Emoji do not Influence Perception of Factual Truth on Twitter",

abstract = "Prior work has shown that Twitter users use skin-toned emoji as an act of self-representation to express their racial/ethnic identity. We test whether this signal of identity can influence readers{\textquoteright} perceptions about the content of a post containing that signal. In a large scale (n=944) pre-registered controlled experiment, we manipulate the presence of skin-toned emoji and profile photos in a task where readers rate obscure trivia facts (presented as tweets) as true or false. Using a Bayesian statistical analysis, we find that neither emoji nor profile photo has an effect on how readers rate these facts. This result will be of some comfort to anyone concerned about the manipulation of online users through the crafting of fake profiles.",

author = "Alexander Robertson and Walid Magdy and Sharon Goldwater",

year = "2021",

month = jun,

day = "1",

doi = "10.36190/2021.06",

language = "English",

booktitle = "Workshop Proceedings of the 15th International AAAI Conference on Web and Social Media",

publisher = "AAAI Press",

note = "4th International Workshop on Emoji Understanding and Applications in Social Media, Emoji 2021 ; Conference date: 07-06-2021 Through 07-06-2021",

url = "http://emoji2021.aiisc.ai/",

}

TY - GEN

T1 - Identity Signals in Emoji do not Influence Perception of Factual Truth on Twitter

AU - Robertson, Alexander

AU - Magdy, Walid

AU - Goldwater, Sharon

PY - 2021/6/1

Y1 - 2021/6/1

N2 - Prior work has shown that Twitter users use skin-toned emoji as an act of self-representation to express their racial/ethnic identity. We test whether this signal of identity can influence readers’ perceptions about the content of a post containing that signal. In a large scale (n=944) pre-registered controlled experiment, we manipulate the presence of skin-toned emoji and profile photos in a task where readers rate obscure trivia facts (presented as tweets) as true or false. Using a Bayesian statistical analysis, we find that neither emoji nor profile photo has an effect on how readers rate these facts. This result will be of some comfort to anyone concerned about the manipulation of online users through the crafting of fake profiles.

AB - Prior work has shown that Twitter users use skin-toned emoji as an act of self-representation to express their racial/ethnic identity. We test whether this signal of identity can influence readers’ perceptions about the content of a post containing that signal. In a large scale (n=944) pre-registered controlled experiment, we manipulate the presence of skin-toned emoji and profile photos in a task where readers rate obscure trivia facts (presented as tweets) as true or false. Using a Bayesian statistical analysis, we find that neither emoji nor profile photo has an effect on how readers rate these facts. This result will be of some comfort to anyone concerned about the manipulation of online users through the crafting of fake profiles.

U2 - 10.36190/2021.06

DO - 10.36190/2021.06

M3 - Conference contribution

BT - Workshop Proceedings of the 15th International AAAI Conference on Web and Social Media

PB - AAAI Press

T2 - 4th International Workshop on Emoji Understanding and Applications in Social Media

Y2 - 7 June 2021 through 7 June 2021

ER -

Identity Signals in Emoji do not Influence Perception of Factual Truth on Twitter

Abstract

Workshop

Access to Document

Fingerprint

Cite this