Tweeting Doomsday Scenarios: Engaging Consumers Online During the Coronavirus Pandemic

Begum Kaplan; Elizabeth G. Miller

Tweeting Doomsday Scenarios: Engaging Consumers Online During the Coronavirus Pandemic

Begum Kaplan^*
, Elizabeth G. Miller

^*Corresponding author for this work

Research output: Contribution to journal › Meeting abstract › peer-review

Abstract

Using text mining methods to analyze 112,641 tweets posted during two different time periods of the Covid-19 pandemic, this research explores the impact of three features – valence, length, and inclusion of URL – on consumer decisions to retweet, like, and reply to tweets in order to gain greater understanding of the features that drive consumer engagement during times of crisis.

Original language	American English
Pages (from-to)	808-809
Number of pages	2
Journal	AMA Winter Academic Conference Proceedings 2021
Volume	32
State	Published - 2021
Externally published	Yes

Keywords

crisis
COVID-19
social media
Twitter
text-mining

Access to Document

http://spiral.lynn.edu/facpubs/1432

Cite this

@article{77743a81ef0a4e6fa93244a9c3b0ab0f,

title = "Tweeting Doomsday Scenarios: Engaging Consumers Online During the Coronavirus Pandemic",

abstract = "Using text mining methods to analyze 112,641 tweets posted during two different time periods of the Covid-19 pandemic, this research explores the impact of three features – valence, length, and inclusion of URL – on consumer decisions to retweet, like, and reply to tweets in order to gain greater understanding of the features that drive consumer engagement during times of crisis.",

keywords = "crisis, COVID-19, social media, Twitter, text-mining",

author = "Begum Kaplan and Miller, \{Elizabeth G.\}",

year = "2021",

language = "American English",

volume = "32",

pages = "808--809",

journal = "AMA Winter Academic Conference Proceedings 2021",

publisher = "American Marketing Association (AMA)",

}

TY - JOUR

T1 - Tweeting Doomsday Scenarios: Engaging Consumers Online During the Coronavirus Pandemic

AU - Kaplan, Begum

AU - Miller, Elizabeth G.

PY - 2021

Y1 - 2021

N2 - Using text mining methods to analyze 112,641 tweets posted during two different time periods of the Covid-19 pandemic, this research explores the impact of three features – valence, length, and inclusion of URL – on consumer decisions to retweet, like, and reply to tweets in order to gain greater understanding of the features that drive consumer engagement during times of crisis.

AB - Using text mining methods to analyze 112,641 tweets posted during two different time periods of the Covid-19 pandemic, this research explores the impact of three features – valence, length, and inclusion of URL – on consumer decisions to retweet, like, and reply to tweets in order to gain greater understanding of the features that drive consumer engagement during times of crisis.

KW - crisis

KW - COVID-19

KW - social media

KW - Twitter

KW - text-mining

UR - http://lynn-lang.student.lynn.edu/login?url=https://search.ebscohost.com/login.aspx?direct=true&db=bth&AN=161339123&site=ehost-live&scope=site

M3 - Meeting abstract

VL - 32

SP - 808

EP - 809

JO - AMA Winter Academic Conference Proceedings 2021

JF - AMA Winter Academic Conference Proceedings 2021

ER -

Tweeting Doomsday Scenarios: Engaging Consumers Online During the Coronavirus Pandemic

Abstract

Keywords

Access to Document

Other files and links

Research output

Tweeting Doomsday Scenarios: Engaging Consumers Online During the Coronavirus Pandemic

Cite this