Improved Hybrid Model for Classification of Text Documents

Abstract

All universities in and around the globe have senate members whose responsibility is to deliberate on matters that affect the smooth running of the university in senate meetings, such matters include, personnel, management, and student matters. Reports are generated at the end of each senate meeting on these matters and are printed on paper or stored in the system without proper grouping of the matters as a result of lack of efficient classification model. This paper proposes hybrid machine learning and deep learning models for the development of efficient classification model for textual documents and tested with reports from senate deliberations from university of Port Harcourt. The dataset for over ten years was collected and pre-processed, noise and other non-alphanumeric values removed by tokenization. Principal component analysis algorithm which is a machine learning approach was used extensively for feature selection and LSTM a deep learning architecture was used to build the model which has the capacity of retaining the content in its memory for a long time which solves the challenges of memory retention in other models. The model built depicts classification accuracy of 99% and the classification application was able to classify decisions made by the senate into different categories which will assist to eliminate conflicting decisions on the floor of any university senate.