Please use this identifier to cite or link to this item:
Title: Gender prediction from tweets: Improving neural representations with hand-crafted features
Authors: Tekir, Selma
Sezerer, Erhan
Polatbilek, Ozan
Tekir, Selma
Sezerer, Erhan
Izmir Institute of Technology. Computer Engineering
Keywords: RNN Model
Model architecture
Neural network-based models
Neural representations
Issue Date: 2019
Source: Tekir, S., Sezerer, E., Polatbilek, O. (2019). Gender prediction from tweets: Improving neural representations with hand-crafted features. Yayın için başvurusu yapılmış metin.
Abstract: 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 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.
Appears in Collections:Computer Engineering / Bilgisayar Mühendisliği

Files in This Item:
File Description SizeFormat 
7251.pdfMakale Dosyası350.33 kBAdobe PDFThumbnail
Show full item record

CORE Recommender

Page view(s)

checked on Aug 3, 2021

Google ScholarTM


This item is licensed under a Creative Commons License Creative Commons