TY - JOUR
T1 - Estimating time-series changes in social sentiment @Twitter in U.S. metropolises during the COVID-19 pandemic
AU - Saito, Ryuichi
AU - Haruyama, Shinichiro
N1 - Funding Information:
M.P. conceived the experiment. All authors contributed to the study design. Material preparation and data collection were performed by B.F., I.V. and R.D. Data analysis was performed by B.F. and M.P. The first draft of the manuscript was written by B.F., I.V. and C.E. All authors commented on previous versions of the manuscript. Financial support was provided by M.D.G. The final version of the manuscript was revised by M.P. and M.D.G. All authors read and approved the final manuscript.
Publisher Copyright:
© 2022, The Author(s).
PY - 2023/4
Y1 - 2023/4
N2 - Since early 2020, the global coronavirus pandemic has strained economic activities and traditional lifestyles. For such emergencies, our paper proposes a social sentiment estimation model that changes in response to infection conditions and state government orders. By designing mediation keywords that do not directly evoke coronavirus, it is possible to observe sentiment waveforms that vary as confirmed cases increase or decrease and as behavioral restrictions are ordered or lifted over a long period. The model demonstrates guaranteed performance with transformer-based neural network models and has been validated in New York City, Los Angeles, and Chicago, given that coronavirus infections explode in overcrowded cities. The time-series of the extracted social sentiment reflected the infection conditions of each city during the 2-year period from pre-pandemic to the new normal and shows a concurrency of waveforms common to the three cities. The methods of this paper could be applied not only to analysis of the COVID-19 pandemic but also to analyses of a wide range of emergencies and they could be a policy support tool that complements traditional surveys in the future.
AB - Since early 2020, the global coronavirus pandemic has strained economic activities and traditional lifestyles. For such emergencies, our paper proposes a social sentiment estimation model that changes in response to infection conditions and state government orders. By designing mediation keywords that do not directly evoke coronavirus, it is possible to observe sentiment waveforms that vary as confirmed cases increase or decrease and as behavioral restrictions are ordered or lifted over a long period. The model demonstrates guaranteed performance with transformer-based neural network models and has been validated in New York City, Los Angeles, and Chicago, given that coronavirus infections explode in overcrowded cities. The time-series of the extracted social sentiment reflected the infection conditions of each city during the 2-year period from pre-pandemic to the new normal and shows a concurrency of waveforms common to the three cities. The methods of this paper could be applied not only to analysis of the COVID-19 pandemic but also to analyses of a wide range of emergencies and they could be a policy support tool that complements traditional surveys in the future.
KW - COVID-19
KW - Coronavirus
KW - GPT-3
KW - Location information
KW - Neural network model
KW - Sentiment analysis
KW - Transformer model
KW - Twitter
UR - http://www.scopus.com/inward/record.url?scp=85141716289&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85141716289&partnerID=8YFLogxK
U2 - 10.1007/s42001-022-00186-4
DO - 10.1007/s42001-022-00186-4
M3 - Article
AN - SCOPUS:85141716289
SN - 2432-2717
VL - 6
SP - 359
EP - 388
JO - Journal of Computational Social Science
JF - Journal of Computational Social Science
IS - 1
ER -