Fig 1.
Number of postings in Japanese about (a) 2014 Tokyo Marathon on BuzzFinder and (b) Noriaki Kasai during the 2014 Winter Olympics.
(a) shows the typical symmetric pattern, while (b) shows the strong asymmetric pattern.
Fig 2.
Power-law growth and decay model without autocorrelation for the Tokyo Marathon data.
The solid line is the observed data and the dotted line is obtained from the power-law growth and decay model.
Table 1.
List of events that took place in 2014, and corresponding search terms which were considered in this study.
Table 2.
Parameter estimates for the power-law growth and decay model without autocorrelation, fitted to the number of postings in Japanese about TokyoMarathon, 2014.
Table 3.
Parameter estimates for the power-law growth and decay model without autocorrelation, fitted to the number of postings in Japanese about Valentine’s day, 2014.
Table 4.
Parameter estimates for the power-law growth and decay model without autocorrelation.
Fig 3.
Valentine’s Day 2014 power-law growth and decay model without autocorrelation. Interpretation of the lines is the same as in Fig 2.
Table 5.
Parameter estimates for the power-law growth and decay model without autocorrelation, fitted to the number of postings in Japanese about Valentine’s day, 2014.
Table 6.
Parameter estimates for AR(2) model, fitted to the number of postings in Japanese about TokyoMarathon, 2014.
Table 7.
Parameter estimates for AR(2) model, fitted to the number of postings in Japanese about Valentine’s day, 2014.
Fig 4.
Fits of the AR(2) model to the number of postings about (a) Children’s Day and (b) Yuko Oshima.
Table 8.
Parameter estimation for the AR(2) model.
Table 9.
Parameter estimates for the unified model.
Table 10.
Comparison of the power-law growth and decay and unified models based on the AIC.