Back

Corowa-kun: Impact of a COVID-19 vaccine information chatbot on vaccine hesitancy, Japan 2021

Kobayashi, T.; Nishina, Y.; Tomoi, H.; Harada, K.; Tanaka, K.; Matsumoto, E.; Horimukai, K.; Ishihara, J.; Sasaki, S.; Inaba, K.; Seguchi, K.; Takahashi, H.; Salinas, J.; Yamada, Y.

2021-05-30 infectious diseases
10.1101/2021.05.26.21257854 medRxiv
Show abstract

BackgroundFew studies have assessed how mobile messenger apps affect COVID-19 vaccine hesitancy. We created a COVID-19 vaccine information chatbot in a popular messenger app in Japan to answer commonly asked questions. MethodsLINE is the most popular messenger app in Japan. Corowa-kun, a free chatbot, was created in LINE on February 6, 2021. Corowa-kun provides instant, automated answers to frequently asked COVID-19 vaccine questions. In addition, a cross-sectional survey assessing COVID-19 vaccine hesitancy was conducted via Corowa-kun during April 5-12, 2021. ResultsA total of 59,676 persons used Corowa-kun during February-April 2021. Of them, 10,192 users (17%) participated in the survey. Median age was 55 years (range 16-97), and most were female (74%). Intention to receive a COVID-19 vaccine increased from 59% to 80% after using Corowa-kun (p < 0.01). Overall, 20% remained hesitant: 16% (1,675) were unsure, and 4% (364) did not intend to be vaccinated. Factors associated with vaccine hesitancy were: age 16 to 34 (odds ratio [OR] = 3.7, 95% confidential interval [CI]: 3.0-4.6, compared to age [&ge;]65), female sex (OR = 2.4, Cl: 2.1-2.8), and history of a previous vaccine side-effect (OR = 2.5, Cl: 2.2-2.9). Being a physician (OR = 0.2, Cl: 0.1-0.4) and having received a flu vaccine the prior season (OR = 0.4, Cl: 0.3-0.4) were protective. ConclusionsCorowa-kun reduced vaccine hesitancy by providing COVID-19 vaccine information in a messenger app. Mobile messenger apps could be leveraged to increase COVID-19 vaccine acceptance.

Matching journals

The top 5 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.