Tekir, SelmaSezerer, ErhanPolatbilek, Ozan03.04. Department of Computer Engineering03. Faculty of Engineering01. Izmir Institute of Technology2019-09-022019-09-022019Tekir, S., Sezerer, E., Polatbilek, O. (2019). Gender prediction from tweets: Improving neural representations with hand-crafted features. Yayın için başvurusu yapılmış metin.https://hdl.handle.net/11147/7251https://doi.org/10.48550/arXiv.1908.09919Author 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 model1 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.eninfo:eu-repo/semantics/openAccesshttp://creativecommons.org/licenses/by-nc/3.0/us/RNN ModelDatasetsModel architectureNeural network-based modelsNeural representationsArticle10.48550/arXiv.1908.09919