An Innovative Academic Question Analyzer for Students Using Support Vector Classifier Algorithm

The goal of this research is to propose an innovative Novel Academic Question analyser for students, which utilizes the Support Vector Classifier (SVC) algorithm, and compares its accuracy with the Naive Bayes algorithm. The proposed system aims to analyze academic questions in a way, leveraging advanced machine learning algorithms to provide accurate results. The sample size for predicting accuracy for Novel Academic Question analyzer systems for students was 4187 in which the t-Test is performed. Group1 and group2 consists of 10 samples each. The question difficulty in the exam is predicted using the Vector Classifier and Naive Bayes algorithms with various training and testing splits. This is when understanding the type of problem or strategy being asked for in the question paper becomes essential. If an unimportant matter interfered with the Credit for the enquiry, it would be missed, i.e. Low-Quality Question Detection in identifying the logic to solve that question. This is when the Academic question paper system comes into existence. SVC identifies objects with 90.44% accuracy while Naive Bayes has accuracy of 76.44%, Loss for support vector classifier (9.55%), and naive bayes (23.55
^%
).