Advances, Systems and Applications
Table 12 Comparison of the test accuracy results of the proposed model with those of previous studies
Author | Model | Accuracy(%) |
|---|---|---|
Derra [44] | Bi-LSTM-Bi-LSTM | 87.46 |
Pushpakumara et al. [50] | RNN | 87 |
Ni and Cao [52] | LTM-GRU | 87.10 |
Le and Mikolov [58] | Paragraph Vector | 87.8 |
Wenpeng et al. [56] | Hieachical Con-vNets | 87.90 |
Nguyen et al. [65] | SVM-NB | 87.95 |
Amulya et al.[49] | RNN | 88 |
Hassan and Mahmood [52] | Conv-Lstm | 88.3 |
Mohaiminul [54] | CNN-LSTM | 89.2 |
Narayanan et al. [76] | NB | 88,80 |
Camacho-Collados and Pilehvar [77] | CNN-LSTM | 88.90 |
Ghorbani, et al. [48] | CNN-LSTM-CNN | 89.02 |
Zhou and Feng [78] | DT | 89.16 |
Wang and Manning [79] | SVM | 89.16 |
Nahal et al. [55] | CNN-LSTM | 89.20 |
Ma and Fan [80] | Bi-LSTM with Attention mechanism | 89.29 |
Sabba et al. [46] | Sequential CNN | 89.47 |
Mesnil et al. [81] | NB-SVM | 91.87 |
Shaukat et al. [53] | Multi Layer Perceptron | 91.9 |
Islam [45] | Bi-GRU-Bi-LSTM | 91.98 |
Amit [43] | MBi-LSTMGLoVe | 92.05 |
Brychcín and Habernal [82] | ME | 92.24 |
Xu et al. [83] | RNN | 92.77 |
Dai and Le [14] | LSTM | 92.80 |
Radford et al. [84] | LSTM | 92.88 |
Johnson and Zhang [86] | CNN | 93.49 |
Dieng et al. [87] | RNN | 93.72 |
Johnson and Zhang [88] | LSTM | 94.06 |
Gray et al. [89] | LSTM | 94.99 |
Proposed Model | MBi-GRUMCONV | 95.34 |