Table 8. Average of proportional performance results on categories with converted dataset.
| Algorithms (Accuracy) | Categories | |||||
|---|---|---|---|---|---|---|
| Peer interactive communication and technical support | Declaration | Presentation | Financial | General acknowledgement | General statement | |
| CNN (80.00%) | 15.71 | 20.00 | 8.57 | 5.71 | 18.57 | 11.43 |
| RNN (69.03%) | 11.43 | 11.54 | 16.24 | 13.42 | 9.50 | 6.89 |
| CNN+Doc2vec (87.93%) | 20.00 | 14.82 | 11.47 | 20.10 | 10.97 | 10.56 |
| kNN (80.40%) | 19.60 | 12.07 | 11.47 | 20.10 | 7.53 | 9.64 |
| Logistic regression (87.15%) | 20.93 | 14.92 | 11.89 | 21.02 | 8.44 | 9.96 |
| Naïve Bayes (87.20%) | 20.24 | 15.05 | 11.38 | 20.93 | 9.73 | 9.87 |
| N-gram language model (85.87%) | 19.96 | 15.00 | 11.38 | 20.56 | 9.78 | 9.18 |
| Average of performance per category | 18.28 | 14.77 | 11.77 | 17.41 | 10.65 | 9.65 |