Understanding panic buying during COVID-19: A text analytics approach

作者：

Highlights：

• Extends compensatory control theory to understand panic buying during the pandemic.

• Focuses on data from 24,153 Twitters users over 14 days during lockdown in Italy.

• Combines text analytics and generalized linear mixed models using big data.

• Results support CCT and find varying impacts of government announcements.

• Contributes to understanding of consumer behavior during pandemics.

摘要

•Extends compensatory control theory to understand panic buying during the pandemic.•Focuses on data from 24,153 Twitters users over 14 days during lockdown in Italy.•Combines text analytics and generalized linear mixed models using big data.•Results support CCT and find varying impacts of government announcements.•Contributes to understanding of consumer behavior during pandemics.

论文关键词：Compensatory control theory,Generalized linear mixed models,Zero-inflation,COVID-19,Social media,Text analytics

论文评审过程：Received 13 September 2020, Revised 29 October 2020, Accepted 20 November 2020, Available online 26 November 2020, Version of Record 10 February 2021.

论文官网地址：https://doi.org/10.1016/j.eswa.2020.114360