An exploratory analysis of alarming and reassuring messages in twitterverse during the coronavirus (Covid-19) epidemic

Naga Vemprala, Rohit Valecha, Patricia Akello, H. Raghav Rao

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Twitter has become one of the widely used crisis communication tools. In the recent coronavirus outbreak, social media users exchange millions of messages ranging from crisis response to awareness creating messages. We conduct an exploratory analysis using tweets collected over initial one month of its outbreak to unveil useful trends and gain insights into managing crisis. Our findings from the analysis present that both alarming and reassuring messages surface during crisis situations, however, it is the reassurance messages that build confidence in individuals to overcome the distress that an epidemic creates. Following the guidelines of Crisis Management, we establish a linguistic based approach to explore the tweets text. Our findings provide insights that the gap between the number of alarming and reassuring messages widen as the epidemic spreads. Our findings also show that significantly, there exists a cluster of similar messages among the deluge of information. Identifying these clusters help manage the crisis situation.

Original languageEnglish
Title of host publication26th Americas Conference on Information Systems, AMCIS 2020
PublisherAssociation for Information Systems
ISBN (Electronic)9781733632546
StatePublished - 2020
Event26th Americas Conference on Information Systems, AMCIS 2020 - Salt Lake City, Virtual, United States
Duration: Aug 10 2020Aug 14 2020

Publication series

Name26th Americas Conference on Information Systems, AMCIS 2020

Conference

Conference26th Americas Conference on Information Systems, AMCIS 2020
Country/TerritoryUnited States
CitySalt Lake City, Virtual
Period08/10/2008/14/20

Keywords

  • Alarming
  • Coronavirus
  • Covid-19
  • Data mining
  • Exploratory analysis
  • Reassurance
  • Text analytics
  • Text mining
  • Word2vec

Fingerprint

Dive into the research topics of 'An exploratory analysis of alarming and reassuring messages in twitterverse during the coronavirus (Covid-19) epidemic'. Together they form a unique fingerprint.

Cite this