Buy Source Code ₹1501
Buy Project Report ₹1001
An Automated Answer Grading System is a machine learning-based Django project that allows teachers to automatically grade student answers in a fast and efficient manner. The system will use natural language processing techniques to analyze and compare the student's answer to the correct answer and assign a grade based on how closely the two match.
The project will consist of a web-based interface that teachers can use to upload student answers and view the results. Teachers will also have the ability to view detailed reports on student performance, including overall scores and breakdowns of individual question scores.
The system will be trained using a dataset of correct and incorrect answers, which will be used to develop the machine learning model that will be used to grade the student's answers. The model will use various natural language processing techniques such as text similarity, sentiment analysis, and topic modeling to compare the student's answer to the correct answer.
The project will be built using the Django web framework and will be hosted on a cloud platform such as AWS or Google Cloud. The frontend of the system will be designed using HTML, CSS, and JavaScript and will provide an easy-to-use and intuitive interface for teachers to interact with.
Overall, the Automated Answer Grading System will be a powerful tool for teachers that will allow them to grade student answers quickly and accurately, freeing up more time for other important teaching tasks.
Dataset
The dataset used is the Kaggle’s Automatic Essay Scoring dataset,can be downloaded from https://www.kaggle.com/c/asap-aes/data
Results
The models were tested using kappa statistic which is intending to compare labelling by different human annotators, not a classifier versus a ground truth. The kappa score is a number between -1 and 1. Scores above .8 are generally considered good agreement,zero or lower means no agreement For this project we have used an Algorithm in which we Combine all the topics into a single model and predicted the score using bi-directional LSTM. kappa score obtained is 0.74