Türkçe Tweetler Üzerinden Yapay Sinir Ağları ile Cinsiyet Tahminlemesi
Loading...
Files
Date
Authors
Journal Title
Journal ISSN
Volume Title
Open Access Color
Green Open Access
No
OpenAIRE Downloads
OpenAIRE Views
Publicly Funded
No
Abstract
Yazar ayrımlaması, yazarı bilinmeyen bir metin üzerinden yazarına dair cinsiyet, yaş ve dil gibi bazı anahtar
özniteliklerin belirlenmesidir. Özellikle güvenlik ve pazarlama alanında önem arz etmektedir. Bu çalışmada, kullanıcıların tweetleri kullanılarak cinsiyetleri tahminlenmektedir. Yinelemeli Sinir Ağı (YSA) ve ilgi mekanizmasının birleşiminden oluşan bir model önerilmiştir. Bildiğimiz kadarıyla bu çalışma Twitter veri
kümesi ile Türkçe’de ilk defa yapılmıştır. Önerilen model Türkçe, İngilizce, İspanyolca ve Arapça dillerinde sınanmış ve sırasıyla 80.63, 81.73, 78.22, 78.5 doğruluk değerlerine ulaşılmıştır. Elde edilen doğruluk değerleri Türkçe’de en gelişkin, diğer dillerde ise rekabetçi bir başarım ortaya koymaktadır.
Author profiling is the characterization of an author through some key attributes such as gender, age, and language. It's an indispensable task especially in security and marketing. In this work, the gender of a Twitter user is predicted using his/her tweets. A model combining a recurrent neural network (RNN) with an attention mechanism is proposed. As far as we know such a predictive analytics is performed in Turkish Twitter dataset for the first time, and the proposed model is tested in Turkish, English, Spanish, and Arabic with accuracy scores of 80.63, 81.73, 78.22, 78.5 respectively. The accuracy values obtained exhibit state-of-the-art in Turkish and competitive performance in the other languages. © 2019 IEEE.
Author profiling is the characterization of an author through some key attributes such as gender, age, and language. It's an indispensable task especially in security and marketing. In this work, the gender of a Twitter user is predicted using his/her tweets. A model combining a recurrent neural network (RNN) with an attention mechanism is proposed. As far as we know such a predictive analytics is performed in Turkish Twitter dataset for the first time, and the proposed model is tested in Turkish, English, Spanish, and Arabic with accuracy scores of 80.63, 81.73, 78.22, 78.5 respectively. The accuracy values obtained exhibit state-of-the-art in Turkish and competitive performance in the other languages. © 2019 IEEE.
Description
27th Signal Processing and Communications Applications Conference, SIU 2019 -- 24 April 2019 through 26 April 2019
Keywords
Attention mechanism, Author profiling, Deep learning, Gender prediction, Neural networks, Twitter dataset
Fields of Science
0202 electrical engineering, electronic engineering, information engineering, 02 engineering and technology
Citation
WoS Q
Scopus Q

OpenCitations Citation Count
6
Volume
Issue
Start Page
1
End Page
4
PlumX Metrics
Citations
CrossRef : 6
Scopus : 1
Captures
Mendeley Readers : 7
Google Scholar™


