Discovering Time-Varying Public Interest for COVID-19 Case Prediction in South Korea Using Search Engine Queries: Infodemiology Study

Seong-Ho Ahn, Kwangil Yim, Hyun-Sik Won, Kang-Min Kim, Dong-Hwa Jeong, Amaryllis Mavragani, June Young Chun, Shihao Yang · 2024

Read Discovering Time-Varying Public Interest for COVID-19 Case Prediction in South Korea Using Search Engine Queries: Infodemiology Study by Seong-Ho Ahn, Kwangil Yim, Hyun-Sik Won, Kang-Min Kim, Dong-Hwa Jeong, Amaryllis Mavragani, June Young Chun, Shihao Yang (2024) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-11686031.txt.

Description

Seong-Ho Ahn and co-authors use web search queries to forecast COVID-19 cases in South Korea in a 2024 study. Case counts guide policy and daily life, and search data can hint at public concern before official counts move. Past models used search terms picked by experts ahead of time, which misses how public interest shifts as a pandemic changes.

The team trained word models on news text and pulled the top 100 words tied to the word Corona in four month windows. They then chose time lags that best matched case counts and built a forecast model. Keywords changed with the phase of the outbreak, from symptoms early on to wider social effects later, which improved the forecast logic.

Catalog record

CREATORSeong-Ho Ahn, Kwangil Yim, Hyun-Sik Won, Kang-Min Kim, Dong-Hwa Jeong, Amaryllis Mavragani, June Young Chun, Shihao Yang
YEAR2024
COLLECTIONPAPERS
FORMATTXT
FILE SIZE52 KB
VERSION1.0
LICENSECC BY 4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/articles/PMC11686031

Browse the full library · About the Tower of Babel