Data from: Public opinion in Japanese newspaper readers’ posts under the prolonged COVID-19 infection spread 2019-2021: Contents analysis using Latent Dirichlet Allocation

These data are based on free description from readers’ posts on Japanese
hardcopy newspaper articles in the public domain. Upon searching
for “coronavirus,” we found 412 reader submissions during the April 7,
2020 to May 25, 2020, 521 during January 8, 2021 to March 21, 2021, 458
during the April 25, 2021 to June 6, 2021, and 519 during July 12, 2021 to
September 30, 2021. Topics of content were extracted by Latent
Dirichlet Allocation, and then calculating the ratio of topic occurrence
in each description.