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. | Â |
| Â | Co-occurrences | [44] | Â | Â |
Topic models | ATAM | [46] | Pearson correlation | r = 0.934 |
| Â | ATAM+ | [47] | Pearson correlation | r = 0.958 |
| Â | HFSTM | [48] | Mean square error (MSE) | MSE = 40.67 |
Machine learning | Neural network | [61] | ACC (Eq. 8) | ACC = 0.9532 |
| Â | SVM | [57] | Pearson correlation | r = 0.93 |
| Â | Â | [56] | Pearson correlation | r = 0.89 |
| Â | Â | [59] | Pearson correlation | r = 0.89 |
| Â | Â | [58] | Â | Â |
| Â | Â | [60] | Pearson correlation | r = 0.9897 |
| Â | Â | [55] | Â | Â |
| Â | Prediction Market using SVR | [64] | Â | Â |
| Â | Naive Bayes | [63] | Sentiment polarity is used to determine the accuracy of the used method (Naive Bayes polarity is 70%) | Â |
Math/Statistical based models | SNEFT | [67] | Pearson correlation | r = 0.9846 |
| Â | ACF | [65] | Pearson correlation | r = 0.767 |
| Â | Numerical-based analysis (SEHA using BOW) | [68] | RMSE | Avg (RMSE) = 1.1 |
Mechanistic disease models | Metpopulation model | [70] | Pearson correlation | r = 0.98 |
| Â | Compartmental model | [35] | Â | Â |
| Â | Agent-based model | [73] | Â | Â |
Keys/Documents filtration | Keys/Documents filtration | [74] | Â | Â |