Identification of Gender based on Blogs using Attention-based Recurrent Neural Network
Sachin Minocha1, Tarun Kumar2, Prem Prakash Agrawal3
1Sachin Minocha, School of Computing Science and Engineering, Galgotias University, Greater Noida, India.
2Tarun Kumar, School of Computing Science and Engineering, Galgotias University, Greater Noida, India.
3Prem Prakash Agrawal, School of Computing Science and Engineering, Galgotias University, Greater Noida, India.

Manuscript received on November 20, 2019. | Revised Manuscript received on November 26, 2019. | Manuscript published on 30 November, 2019. | PP: 3152-3158 | Volume-8 Issue-4, November 2019. | Retrieval Number: D8009118419/2019©BEIESP | DOI: 10.35940/ijrte.D8009.118419

Open Access | Ethics and Policies | Cite  | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)

Abstract: With the digitization, the importance of content writing is being increased. This is due to the huge improvement in accessibility and the major impact of digital content on human beings. Due to veracity and huge demand for digital content, author profiling becomes a necessity to identify the correct person for particular content writing. This paper works on deep neural network models to identify the gender of author for any particular content. The analysis has been done on the corpus dataset by using artificial neural networks with different number of layers, long short term memory based Recurrent Neural Network (RNN), bidirectional long short term memory based RNN and attention-based RNN models using mean absolute error, root mean square error, accuracy, and loss as analysis parameters. The results of different epochs show the significance of each model.
Keywords: Deep Learning, LSTM, Bidirectional LSTM, Attention-based LSTM, Embedding, RNN, Activation Functions.
Scope of the Article: Deep Learning.