ABSTRACT
Massive Open Online Courses (MOOCs) have shown rapid development in recent years, allowing learners to access high-quality digital material. Because of facilitated learning and the flexibility of the teaching environment, the number of participants is rapidly growing. However, extensive research reports that the high attrition rate and low completion rate are major concerns. In this paper, the early identification of students who are at risk of withdrew and failure is provided. Therefore, two models are constructed namely at-risk student model and learning achievement model. The models have the potential to detect the students who are in danger of failing and withdrawal at the early stage of the online course. The result reveals that all classifiers gain good accuracy across both models, the highest performance yield by GBM with the value of 0.894, 0.952 for first, second model respectively, while RF yield the value of 0.866, in at-risk student framework achieved the lowest accuracy. The proposed frameworks can be used to assist instructors in delivering intensive intervention support to at-risk students.
EXISITNG :
To build an accurate at-risk student prediction model, researchers investigated the reasons behind course withdrawal. This has been attributed to a number of factors. The main reason for students dropping out of online courses is the lack of motivation . Researchers suggested that students’ motivational levels in online courses either decrease or increase according to social, cognitive and environmental factors . The motivational trajectory is an important indicator of student dropout. Motivational trajectories can be measured by exploring changes in learner behaviour across courses. Until now, most researchers did not pay attention in examining the association between motivational trajectories, student learning achievement and at-risk students in the online setting.
PROPOSED SYSTEM:
In this work, Convolutional Neural Networks (CNN) were combined with Recurrent Neural Networks (RNN) to predict whether students are at risk of withdrawal from the online course ‘‘XuetangX’’ in the next ten days. Student records were structured according to a sequence of time-stamps and contained various attributes such as event time, event type and student enrolment date. The hybrid neural network model consists of two parts, namely, the lower and upper parts. In the lower part, the hidden layer of CNN was utilized to extract features automatically. In the upper part, RNN was used to make a prediction by aggregating and combining the extracted features at each time. The model was compared with various baseline methods. The results indicated similar performance across all models. The F1-score results were reported in the range of 90.74-92.48. Although there was similarity in performance, the authors argued that the ConRec Network model is more efficient than baseline methods, as it has the ability to extract the features automatically from student records without the need of feature engineering.
SYSTEM REQUIREMENTS
SOFTWARE REQUIREMENTS:
• Programming Language : Python
• Font End Technologies : TKInter/Web(HTML,CSS,JS)
• IDE : Jupyter/Spyder/VS Code
• Operating System : Windows 08/10
HARDWARE REQUIREMENTS:
Processor : Core I3
RAM Capacity : 2 GB
Hard Disk : 250 GB
Monitor : 15″ Color
Mouse : 2 or 3 Button Mouse
Key Board : Windows 08/10
