Leveraging Business Intelligence and Student Feedback for Enhancing Teaching and Learning in Higher Education

The main objective of this study is to examine data, improve teaching quality, and accelerate ongoing development in higher education through the use of Business Intelligence (BI) tools and the incorporation of student feedback. Business Intelligence and other forms of technology play a critical role in improving the efficiency, effectiveness, and individualization of educational services. Higher education has a serious problem due to the lack of a well-defined plan to incorporate student feedback and data analytics into the classroom. Due to its absence, the potential to gain insightful information and improve educational experiences is hindered. A machine learning hybrid model is trained and proposed known as Convolution Neural Network (CNN) + Long-Short Term Memory (LSTM) model to predict student feedback. The investigation reveals that students provide feedback in various forms, encompassing positive, negative, and neutral responses concerning faculty performance. The proposed hybrid model achieves an accuracy of 90.34% and a loss of 0.285 in classifying the sentiment analysis of the students. Also, the proposed hybrid model performs better as compared with other conventional approaches.