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

Table 13

Obtained results (accuracy, %) for age and gender classification using SVM classifier on the PAN author profiling 2015 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)	59.83	56.67	67.00	73.00
D2V (1 + 2-grams)	68.33	69.61	67.00	69.00
D2V (1 + 2 + 3-grams)	69.50	72.28	65.00	71.00