Gender Prediction from Tweets: Improving Neural Representations with Hand-Crafted Features
This work addresses author profiling for social media analysis, but it is incremental as it combines existing neural and feature-based methods.
The authors tackled gender prediction from tweets by proposing an RNN with attention model and enhancing it with hand-crafted n-gram features, achieving state-of-the-art performance in English and competitive results in Spanish and Arabic.
Author profiling is the characterization of an author through some key attributes such as gender, age, and language. In this paper, a RNN model with Attention (RNNwA) is proposed to predict the gender of a twitter user using their tweets. Both word level and tweet level attentions are utilized to learn 'where to look'. This model (https://github.com/Darg-Iztech/gender-prediction-from-tweets) is improved by concatenating LSA-reduced n-gram features with the learned neural representation of a user. Both models are tested on three languages: English, Spanish, Arabic. The improved version of the proposed model (RNNwA + n-gram) achieves state-of-the-art performance on English and has competitive results on Spanish and Arabic.