Improving Feature Representation Based on a Neural Network for Author Profiling in Social Media Texts

Table 16

Obtained results (accuracy, %) for age and gender classification using SVM classifier on the PAN author profiling 2016 Spanish training corpus under 10-fold cross-validation with vectors extracted only from the training data.

Feature set	Age		Gender
	SVM-NP	SVM-WP	SVM-NP	SVM-WP
D2V (1-gram)	44.73	42.94	73.17	73.33
D2V (1 + 2-grams)	43.57	43.21	74.42	75.13
D2V (1 + 2 + 3-grams)	44.53	45.19	74.74	79.10