Parallel Attention-Driven Model for Student Performance Evaluation

• DOI: 10.3390/computers13090242
• Publication Date: 2024-09-23T13:15:07Z
• Authors: Deborah Olaniyan; Julius Olaniyan; Ibidun Christiana...; Bukohwo Michael E...; Olorunfemi Paul B...
• Keywords: student; multi-task; Electronic computers. Computer science; deep learning; QA75.5-76.95; attention mechanism; e-learning; performance

This study presents the development and evaluation of a Multi-Task Long Short-Term Memory (LSTM) model with an attention mechanism for predicting students’ academic performance. The research is motivated by need efficient tools to enhance student assessment support tailored educational interventions. tackles two tasks: overall performance (total score) as regression task classifying levels (remarks) classification task. By handling both tasks simultaneously, it improves computational efficiency resource utilization. dataset includes metrics such Continuous Assessment, Practical Skills, Presentation Quality, Attendance, Participation. achieved strong results, Mean Absolute Error (MAE) 0.0249, Squared (MSE) 0.0012, Root (RMSE) 0.0346 For task, perfect scores accuracy, precision, recall, F1 score 1.0. enhanced focusing on most relevant features. demonstrates effectiveness LSTM in data analysis, offering reliable tool