Skip to main content

Advertisement

Springer Nature is making SARS-CoV-2 and COVID-19 research free. View research | View latest news | Sign up for updates

Table 2 Summary of the reviewed methods and techniques

From: A review of influenza detection and prediction through social networking sites

Method category Method name Study reference Performance metric Metric value
Graph data mining Graph data Mining [23] Pearson correlation r = 0.545
Text mining Historical patterns [45] The precision for 1-day prediction is 0.8 (with mean of 0.52) and 0.6 (with mean of 0.46) for 7-days prediction.  
  Co-occurrences [44]   
Topic models ATAM [46] Pearson correlation r = 0.934
  ATAM+ [47] Pearson correlation r = 0.958
  HFSTM [48] Mean square error (MSE) MSE = 40.67
Machine learning Neural network [61] ACC (Eq. 8) ACC = 0.9532
  SVM [57] Pearson correlation r = 0.93
   [56] Pearson correlation r = 0.89
   [59] Pearson correlation r = 0.89
   [58]   
   [60] Pearson correlation r = 0.9897
   [55]   
  Prediction Market using SVR [64]   
  Naive Bayes [63] Sentiment polarity is used to determine the accuracy of the used method (Naive Bayes polarity is 70%)  
Math/Statistical based models SNEFT [67] Pearson correlation r = 0.9846
  ACF [65] Pearson correlation r = 0.767
  Numerical-based analysis (SEHA using BOW) [68] RMSE Avg (RMSE) = 1.1
Mechanistic disease models Metpopulation model [70] Pearson correlation r = 0.98
  Compartmental model [35]   
  Agent-based model [73]   
Keys/Documents filtration Keys/Documents filtration [74]