A new type of eye movement model based on recurrent neural networks for simulating the gaze behavior of human reading.

Wang, Xiaoming; Zhao, Xinbo; Ren, Jinchang

Abstract

Traditional eye movement models are based on psychological assumptions and empirical data that are not able to simulate eye movement on previously unseen text data. To address this problem, a new type of eye movement model is presented and tested in this paper. In contrast to conventional psychology-based eye movement models, ours is based on a recurrent neural network (RNN) to generate a gaze point prediction sequence, by using the combination of convolutional neural networks (CNN), bidirectional long short-term memory networks (LSTM), and conditional random fields (CRF). The model uses the eye movement data of a reader reading some texts as training data to predict the eye movements of the same reader reading a previously unseen text. A theoretical analysis of the model is presented to show its excellent convergence performance. Experimental results are then presented to demonstrate that the proposed model can achieve similar prediction accuracy while requiring fewer features than current machine learning models.

Citation

WANG, X., ZHAO, X. and REN, J. 2019. A new type of eye movement model based on recurrent neural networks for simulating the gaze behavior of human reading. Complexity [online], 2019: complex deep learning and evolutionary computing models in computer vision, article ID 8641074. Available from: https://doi.org/10.1155/2019/8641074

• Journal Article Type: Article
• Acceptance Date: Feb 27, 2019
• Online Publication Date: Mar 24, 2019
• Publication Date: Apr 1, 2019
• Deposit Date: May 6, 2022
• Publicly Available Date: Jun 7, 2022
• Journal: Complexity
• Print ISSN: 1076-2787
• Electronic ISSN: 1099-0526
• Publisher: Hindawi
• Peer Reviewed: Peer Reviewed
• Volume: 2019
• Article Number: 8641074
• DOI: https://doi.org/10.1155/2019/8641074
• Keywords: Eye movement; Eye movement models; Recurrent neural network (RNN); Convolutional neural networks (CNN); Long short-term memory networks (LSTM); Conditional random fields (CRF)
• Public URL: https://rgu-repository.worktribe.com/output/1085584