Skip to main content
. 2018 Mar 20;20(5):933–948. doi: 10.1007/s10796-018-9844-9

Table 5.

Recall (F-score) of tweets, using (i) bag-of-words features (BOW), (ii) proposed features (PRO)

Train set Test set
Ebola MERS
BOW PRO BOW PRO
Ebola 0.84(0.85) 0.84(0.84) 0.65(0.66) 0.76(0.76)
MERS 0.66(0.65) 0.75(0.75) 0.88(0.88) 0.81(0.81)

In-domain classification results are represented by italic entries. For each train-test pair, the accuracy of better performing system has been boldfaced