scholarly journals Investigating the Differences in Predictive Oculomotor Strategies using Long Short-Term Memory Recurrent Neural Network Models

2018 ◽  
Vol 18 (10) ◽  
pp. 184
Author(s):  
Kamran Binaee ◽  
Rakshit Kothari ◽  
Jeff Pelz ◽  
Gabriel Diaz
2019 ◽  
Vol 8 (4) ◽  
pp. 3152-3158

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.


Sign in / Sign up

Export Citation Format

Share Document