Abstract
With the formation and growth of the company, corporate law is continuously established and enhanced. It significantly contributes to the company’s healthy growth and brings business operations inside the legal framework. As a result, corporate law education is crucial for employees, particularly directors. Fundamentally, corporate law education is a learning process. The metaverse period has increased learners’ needs for learning environments, and human-computer interaction technology will offer all-encompassing support for the smart learning environment. The board of directors needs to adequately monitor each director’s learning level as they study corporate law, which will inevitably be detrimental to the company’s long-term growth. The most efficient method to address this issue is to use eye movement data to mine different eye movement patterns, followed by an analysis of the learning state of corporate law of directors. The scanning path analysis is used to examine the similarities and differences of the directors’ eye movement behaviors during the study of corporate law to enhance the state of corporate law learning. However, the learning status of corporate law cannot be determined only by the eye tracking of directors. We employ the convolutional neural networks (CNN) -based emotion recognition model to provide the directors constructive criticism about their learning state and offer suggestions for the learning mode. The experimental results demonstrate that time series-based eye movement pattern mining can identify directors’ viewing habits, and clustering can reveal different learning strategies that can be used to evaluate directors’ corporate law learning status. Additionally, the CNN-based emotion recognition model experiment also shows that the established model has an accuracy of 97.0035% and an F1 of 0.9412 in the CASIA-FaceV5 dataset, which helps evaluate the emotions of directors when learning company law.
Disclosure statement
No potential conflict of interest was reported by the author(s).
Data availability statement
All data used to support the findings of the study is included within this paper.
Additional information
Notes on contributors
Qiao Du
Qiao Du is pursuing for a Ph.D at China University of Political Science and Law. Her research interests include corporate law, education, human-computer interaction, data science, etc.
Murali Subramanian
Murali Subramanian is an associate professor at Vellore Institute of Technology. He has 9 years experience in teaching. His research interests include wireless network, data science, etc.
Daohua Pan
Daohua Pan received her Ph.D from Harbin Institute of Technology in 2021. She is currently a senior lecture at Harbin Institute of Technology and Heilongjiang Minzu College. Her research interests include AI; education technology, 5G, etc.