Table 4.
Classification accuracy achieved by the two machine learning algorithms on the SD versus NC categorization task, using the full lexical feature set (top) and only those features with positive information gain values (bottom).
Naïve Bayes Gaussian |
Naïve Bayes multinomial |
|||||
---|---|---|---|---|---|---|
Classification | SD | NC | SD | NC | ||
All features | Category | SD (n = 32) | 32 | 0 | 29 | 3 |
NC (n = 10) | 1 | 9 | 0 | 10 | ||
Accuracy | .98 | .93 | ||||
Selected features |
Category | SD (n = 32) | 32 | 0 | 29 | 3 |
NC (n = 10) | 0 | 10 | 0 | 10 | ||
Accuracy | 1 | .93 |