Skip to main content

Table 2 Overall prediction performance

From: Information cascades prediction with attention neural network

 t = 1*t = 2*t = 3*
MSEMAEMSEMAEMSEMAE
Twitter
 Features-linear3.8211.5363.5111.4793.4231.42
 SVR3.7981.5293.0281.3843.3821.411
 SEISMIC3.7701.5272.9541.313
1.462
3.3191.408
 DeepCas3.7251.4933.496 3.3081.395
 Proposed2.6091.2652.3491.1672.3001.14
AMiner
 Features-linear2.4291.1972.1361.0891.8801.067
 SVR2.4191.1942.1951.1231.8651.066
 SEISMIC2.4171.1932.2821.1361.8521.061
 DeepCas2.2391.1271.9871.0721.6741.056
 Proposed2.1721.1161.6721.0421.5341.003
  1. p.s. t = 1*, where ‘*’ denotes hour for Twitter (year for AMiner)