Table 2. Parameters Doc2Vec algorithm.
| Parameters | Value | Description |
|---|---|---|
| vector_size (int, optional) | 300 | Dimensionality of the feature vectors |
| alpha (float, optional) | 0.025 | The initial learning rate |
| min_alpha (float, optional) | 0.00025 | Learning rate will linearly drop to min_alpha as training progresses |
| workers (int, optional) | 18 | Use these many worker threads to train the model (= faster training with multicore machines) |
| min_count (int, optional) | 3 | Ignores all words with total frequency lower than this |
| epochs (int, optional) | 30 | Number of iterations (epochs) over the corpus |
| dm ({1,0}, optional) | 1 | Defines the training algorithm. If dm = 1, ‘distributed memory’ (PV-DM) is used. Otherwise, distributed bag of words (PV-DBOW) is employed |