Project Home
PDF ACCESS

Authors

Nada Ahmed , Mariam Yasser, Rawan Ahmed, and  Philip George

Publishing Date

7 March 2022

Abstract

The grading of short answer questions has become a headache recently. As a result, the system’s main goal is to build an automatic correction model for subjective questions, which will make the process of checking the essay questions answers easier. The input answers are reference answers and the student answers then the system will correct and give the score. The system has been categorized into some steps firstly, preprocessing of data using tokenization, stop word removal, porter stemmer, Then these answers were transformed into vectors using TF-IDF, which is a frequency computation technique. Then used Cosine similarity to measure the similarity of the answers. To evaluate the performance of the proposed system. We also used latent semantic analysis (LSA) to increase accuracy cite{LSA}. Also we used 6 algorithms in machine learning as Decision tree, logistic regression, naive Bayescite{article}, knn, random forest,and svm. Along with GRU and LSTM concerning deep learning models.

1.1 Purpose

The architecture and system design of the CORRECTA web application are described in this software design description (SDD), which translates the requirements into software components, data, and a user interface. The system is designed to help the instructor in correcting the essay questions

1.2 Scope

The Software Design Document’s goal is to encourage software development by giving a fully described system design. This document defines method of how the system is designed and planned to be developed and also defines important details for system.

1.3 Overview

The Software design document will describe in details the architecture of Auto correction for subjective questions. The first section is the introduction which will discuss the document’s purpose, scope, and overview. In the second section we will talk about the systems overview, scope, goals and timeline. In the third section the system’s design viewpoints are discussed. It includes the following (context, composition, logical, patterns use, algorithm, interaction, and interface viewpoint). While in the fourth section; the Data Design, which consist of data, dataset and database design description. In the fifth section; the Human Interface Design, which includes user interface and screen images. Finally, the sixth section includes a requirements matrix, which is a table that describes the system’s functions and status.

1.4 Intended audience

The project team is the one that is charged with this document in order to monitor the project. The stakeholders that can use this system are instructors, students and admins.