A New Student Modeling Technique With Convolutional Neural Networks: LearnerPrints

Abstract

Student modeling is one of the most important processes in adaptive systems. Although learning is individual, a model can be created based on patterns in student behavior. Since a student model can be created for more than one student, the use of machine learning techniques in student modeling is increasing. Artificial neural networks (ANNs), which form one group of machine learning techniques, are among the methods most frequently used in learning environments. Convolutional neural networks (CNNs), which are specific types of these networks, are used effectively for complex problems such as image processing, computer vision and speech recognition. In this study, a student model was created using a CNN due to the complexity of the learning process, and the performance of the model was examined. The student modeling technique used was named LearnerPrints. The navigation data of the students in a learning management system were used to construct the model. Training and test data were used to analyze the performance of the model. The classification results showed that CNNs can be used effectively for student modeling. The modeling was based on the students’ achievement and used the students’ data from the learning management system. The study found that the LearnerPrints technique classified students with an accuracy of over 80%.

An Evaluation of the Use of Artificial Intelligence Applications in Online Education

“…In addition to personalized learning experiences through AI algorithms, it has become possible for instructors to analyze learners' data to predict their performance and provide them with additional support. AI performance prediction models have been used in online higher education as an effective method to accurately predict students' learning performance using student learning data and AI algorithms and to take measures and steps of improvement accordingly (Aydogdu, 2021;Tomasevic et al, 2020). This allows instructors to identify students at risk of failure and provide interventions to help them succeed.…”

Integration of artificial intelligence performance prediction and learning analytics to improve student learning in online engineering course

“…Online higher education has attracted extensive attention in the COVID-19 period with a goal to improving the quality of personalization, monitoring and evaluation in learning (Hwang et al, 2020 ). AI performance prediction model has been used as a promising method in online higher education to accurately predict and monitor students’ learning performance using student learning data and AI algorithms (Aydogdu, 2021 ; Sandoval et al, 2018 ; Tomasevic et al, 2020 ). The existing AI performance prediction models have been developed from the AI model perspective: with the objective of predicting the learning performance that students are likely to achieve given all the input information (Cen et al, 2016 ).…”

Research on the construction and sustainable development of online teaching model for universities based on deep learning

“…A convolution can computationally extract one kind of feature matrix of the data, so multiple convolution kernels can be set up to obtain a multidimensional feature matrix. The pooling layer is generally connected after the convolution layer to perform a down-sampling processing of pictures after the convolution operation, which is used to compress the amount of data and parameters to reduce the number of operations for network training and to play a role in preventing overfitting [19][20].…”