Automated categorization of student's query

Abstract

Students face many problems like mental stress, peer pressure, and health issues in college, but they do not report these due to lack of awareness, shy nature, or fear. This article proposes a platform that will unite students and the authority responsible for resolving these problems. The platform's core has a query classifier that uses text classification for categorizing the query. Text classification has already been used widely in many different problems like the chatbot, query categorization, intent, and detection. This is the first attempt to use text classification for categorizing students' queries. The query and category data have been collected from more than 400 students. Data pre-processing is done to convert textual data into numerical data. Dimensionality reduction has been applied in order to minimize the number of features. Five different machine learning (ML) approaches are applied to evaluate the performance of query categorization. K-fold cross-validation has been applied, and the ML approaches have been compared using accuracy, precision, recall, and F1-measure. The results show that Multi-Layer Perception with Back Propagation (MLP with BP) performs better than other classifiers in terms of all the metrics.