Gender Prediction From Tweets: Improving Neural Representations With Hand-Crafted Features
Loading...
Files
Date
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
Open Access Color
Green Open Access
Yes
OpenAIRE Downloads
OpenAIRE Views
Publicly Funded
No
BIP! Indicators
Impulse
Average
Influence
Average
Popularity
Average
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.
Description
Keywords
RNN Model, Datasets, Model architecture, Neural network-based models, Neural representations, FOS: Computer and information sciences, Computer Science - Machine Learning, Computer Science - Computation and Language, Machine Learning (stat.ML), Machine Learning (cs.LG), Neural network-based models, Neural representations, Statistics - Machine Learning, Datasets, Computation and Language (cs.CL), RNN Model, Model architecture
Fields of Science
02 engineering and technology, 01 natural sciences, 0202 electrical engineering, electronic engineering, information engineering, 0105 earth and related environmental sciences
Citation
Tekir, S., Sezerer, E., Polatbilek, O. (2019). Gender prediction from tweets: Improving neural representations with hand-crafted features. Yayın için başvurusu yapılmış metin.
WoS Q
N/A
Scopus Q
N/A
OpenCitations Citation Count
N/A
Source
arXiv
Volume
Issue
Start Page
End Page
