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

Table 11

Obtained results (accuracy, %) for age and gender classification on the PAN author profiling 2016 Dutch training corpus under 10-fold cross-validation.

Feature set	Gender
	LR-NP	LR-WP	SVM-NP	SVM-WP
D2V (1-gram)	74.74	77.60	71.09	75.26
D2V (1 + 2-grams)	70.83	75.78	71.09	75.52
D2V (1 + 2 + 3-grams)	73.44	76.04	70.31	73.44
Character 3-grams	76.56	72.66	74.48	72.92
Bag-of-Words	74.48	71.88	74.74	70.83