The use of machine learning to understand human learning
Refereed conference paper presented and published in conference proceedings



摘要Education is a process that involves a complex relationship between the learning environment and the individual student’s unique personalities and capabilities. Traditionally this relationship is studied and modelled using statistical methods such as linear regression. Due to the complexity of human nature and societal influences, the accuracy and reliability of the model using the traditional methods may not be satisfactory. We have adopted machine learning techniques in developing our educational model on data collected from various sources of a foundational course in the Chinese University of Hong Kong. This includes objective data such as student grades, their prior knowledge, their family background, the learning environmental conditions, and subjective data such as questionnaire that measures student’s perception and reflection on their learning process and status. This mix of objective and subjective data is not commonly found in other applications of machine learning, yet provided a platform for it to excel. Preliminary result of our study indicates that our model has achieved an improvement in its predictive power on student’s final achievement. The study provides insights on how machine learning can be used to help us to understand and improve our own learning process.
著者Kiang Kai Ming
會議名稱2017 International Conference on Deep Learning Technologies (ICDLT 2017)
會議論文集題名Proceedings of the 2017 International Conference on Deep Learning Technologies
關鍵詞Education, Machine learning, Human learning, questionnaire data

上次更新時間 2018-09-05 於 14:39