Title: Automated Answer Grading System Using Machine

Learning

ABSTRACT:

The Automated Answer Grading System (AAGS) is a machine

learning-based project designed to evaluate and grade student
answers automatically. The system leverages Natural Language
Processing (NLP) and machine learning algorithms to assess the
quality, relevance, and accuracy of answers provided by
students.

By automating the grading process, the system aims to reduce

the workload on educators, ensure consistency in grading, and
provide instant feedback to students.

The proposed system is capable of handling both short and long-

form answers, making it suitable for a wide range of educational
applications.
EXISTING SYSTEM:

1. Manual Grading:
o Educators manually grade each answer, which is time-
consuming and prone to human error.

o Inconsistent grading due to subjective evaluation.

o Limited scalability for large classes or online courses.

2. Rule-Based Systems:
o Some systems use predefined rules or keyword matching
to grade answers.

o Lack flexibility and cannot handle complex or nuanced

answers.

o Unable to understand context or semantic meaning.

3. Multiple-Choice Grading:
o Automated systems are limited to grading multiple-
choice questions.

o Cannot evaluate open-ended or subjective answers.

PROPOSED SYSTEM:

The proposed Automated Answer Grading System uses

advanced machine learning techniques to overcome the
limitations of existing systems. Key features include:

1. Natural Language Processing (NLP):

o Understands the context and semantics of student
answers.

o Evaluates answers based on relevance, coherence, and

accuracy.

2. Machine Learning Models:

o Utilizes models like BERT, GPT, or custom-trained
models for text classification and similarity scoring.

o Adapts to different subjects and question types.

3. Scalability:
 o Can handle a large number of answers simultaneously,
making it suitable for online education platforms.

4. Instant Feedback:
o Provides immediate feedback to students, helping
them understand their mistakes and improve.

5. Customizable Grading Rubrics:

o Allows educators to define grading criteria and
weightage for different aspects of the answer.
 SYSTEM CONFIGURATION

Hardware Requirements:

1. Processor: Intel i5 or higher (or equivalent AMD

processor).

2. RAM: 8 GB or higher.

3. Storage: 500 GB HDD or 256 GB SSD.

4. GPU: NVIDIA GTX 1060 or higher (for training machine

learning models).

Software Requirements:

1. Operating System: Windows 10/11, Linux, or macOS.

2. Programming Language: Python 3.x.

 3. Libraries and Frameworks:
o TensorFlow, PyTorch, or Scikit-learn for machine
learning.

o NLTK, SpaCy, or Hugging Face Transformers for

NLP.

o Flask or Django for web-based interface (optional).

4. Database: MySQL.

ARCHITECTURE DIAGRAM:
1. User Interface (UI):
o Web-based or desktop interface for students and
educators.
 o Students submit answers, and educators define grading
rubrics.

2. Preprocessing Module:
o Cleans and preprocesses the input text (e.g.,
tokenization, stopword removal, stemming).

o Converts text into numerical representations (e.g., word

embeddings).

3. Machine Learning Model:

o Trained on a dataset of graded answers to learn patterns
and grading criteria.

o Uses NLP techniques to evaluate the semantic similarity

between the student's answer and the reference answer.

4. Grading Engine:
o Applies the trained model to assign scores based on
relevance, accuracy, and coherence.

o Provides detailed feedback on the answer.

5. Database:
 o Stores student answers, reference answers, and grading
results.

o Allows educators to review and modify grades if

necessary.

6. Feedback Module:
o Generates instant feedback for students, highlighting
strengths and weaknesses in their answers.

7. Admin Panel:
o Allows administrators to manage users, courses, and
grading rubrics.
Modules Description

1. User Management Module

Purpose: Handle authentication, authorization, and role-based

access control
Components:
 Authentication Service: Login/logout, password reset
(Django Auth)
 Role Manager:
o Teachers (Upload answers, view reports)

o Students (View grades)

o Admins (Manage users, update models)

2. Answer Processing Module

Purpose: Preprocess and prepare student answers for grading

Functions:
 Bulk Upload Handler: CSV/PDF parser (PyPDF2,
pandas)
Dependencies: NLTK/spaCy, Django file upload handlers
3. Grading Engine (Core Module)

Purpose: Execute ML-based answer evaluation

Components:
 Similarity Analyzer: Cosine similarity between
student/reference answers
 Score Calculator: Map model output to grading rubric
(e.g., 0-10 scale)
Dependencies: TensorFlow/Keras,
sklearn.metrics.pairwise

4. Analytics & Reporting Module

Purpose: Generate actionable insights from graded answers

Functions:
 Class Statistics: Average score, question-wise performance
 Student Progress Tracker: Historical grade trends
 Report Generator: PDF/Excel exports (ReportLab,
pandas)
Dependencies: Matplotlib for visualizations, Django
templates
5. Model Training Module

Purpose: Retrain and improve the grading model

Workflow:
1. Admin uploads new training data (Kaggle dataset format)
2. Automated pipeline:
3. Model versioning with performance metrics (kappa score
tracking)

Feasibility Study

The feasibility of the project is analyzed in this phase and

business proposal is put forth with a very general plan for the

project and some cost estimates. During system analysis the

feasibility study of the proposed system is to be carried out. This

is to ensure that the proposed system is not a burden to the

company. For feasibility analysis, some understanding of the

major requirements for the system is essential.

Three key considerations involved in the feasibility analysis are

 ECONOMICAL FEASIBILITY

 TECHNICAL FEASIBILITY

 SOCIAL FEASIBILITY

ECONOMICAL FEASIBILITY

This study is carried out to check the economic impact

that the system will have on the organization. The amount of

fund that the company can pour into the research and

development of the system is limited. The expenditures must be

justified. Thus the developed system as well within the budget

and this was achieved because most of the technologies used are

freely available. Only the customized products had to be

purchased.
TECHNICAL FEASIBILITY

This study is carried out to check the technical

feasibility, that is, the technical requirements of the system. Any

system developed must not have a high demand on the available

technical resources. This will lead to high demands on the

available technical resources. This will lead to high demands

being placed on the client. The developed system must have a

modest requirement, as only minimal or null changes are

required for implementing this system.

SOCIAL FEASIBILITY

The aspect of study is to check the level of acceptance of

the system by the user. This includes the process of training the
user to use the system efficiently. The user must not feel

threatened by the system, instead must accept it as a necessity.

The level of acceptance by the users solely depends on the

methods that are employed to educate the user about the system

and to make him familiar with it. His level of confidence must

be raised so that he is also able to make some constructive

criticism, which is welcomed, as he is the final user of the

system.
 UML DIAGRAMS

UML stands for Unified Modeling Language. UML is a

standardized general-purpose modeling language in the field of

object-oriented software engineering. The standard is managed,

and was created by, the Object Management Group.

The goal is for UML to become a common language for

creating models of object oriented computer software. In its

current form UML is comprised of two major components: a

Meta-model and a notation. In the future, some form of method

or process may also be added to; or associated with, UML.

 The Unified Modeling Language is a standard language for

specifying, Visualization, Constructing and documenting the

artifacts of software system, as well as for business modeling

and other non-software systems.

The UML represents a collection of best engineering

practices that have proven successful in the modeling of large

and complex systems.

The UML is a very important part of developing objects

oriented software and the software development process. The

UML uses mostly graphical notations to express the design of

software projects.
GOALS:

The Primary goals in the design of the UML are as follows:

1. Provide users a ready-to-use, expressive visual modeling

Language so that they can develop and exchange

meaningful models.

2. Provide extendibility and specialization mechanisms to

extend the core concepts.

3. Be independent of particular programming languages and

development process.

4. Provide a formal basis for understanding the modeling

language.

5. Encourage the growth of OO tools market.

 6. Support higher level development concepts such as

collaborations, frameworks, patterns and components.

7. Integrate best practices.

USE CASE DIAGRAM:

A use case diagram in the Unified Modeling Language (UML) is a type of

behavioral diagram defined by and created from a Use-case analysis. Its purpose is

to present a graphical overview of the functionality provided by a system in terms

of actors, their goals (represented as use cases), and any dependencies between

those use cases. The main purpose of a use case diagram is to show what system

functions are performed for which actor. Roles of the actors in the system can be

depicted.

USE CASE DIAGRAM:

SEQUENCE DIAGRAM:

A sequence diagram in Unified Modeling Language (UML) is a kind of interaction

diagram that shows how processes operate with one another and in what order. It is

a construct of a Message Sequence Chart. Sequence diagrams are sometimes called

event diagrams, event scenarios, and timing diagrams.

SEQUENCE DIAGRAM:
DATA FLOW DIAGRAM:

A Data Flow Diagram (DFD) is a diagram that describes the flow of

data and the processes that change data throughout a system. It’s a structured
analysis and design tool that can be used for flowcharting in place of or in
association with information. Oriented and process oriented system flowcharts.
Four basic symbols are used to construct data flow diagrams. They are
symbols that represent data source, data flows, and data transformations and
data storage. The points at which data are transformed are represented by
enclosed figures, usually circles, which are called nodes.
Data Flow Diagram Symbols

- Source or Destination of data

- Data Flow

- Process

- Storage

When analysts prepare the Data Flow Diagram, they specify the user
needs at a level of detail that virtually determines the information flow into
and out of the system and the required data resources.
The network is constructed by using a set of symbols that do not imply physical
implementation. The Data Flow Diagram reviews the current physical system,
prepares input and output specification, and specifies the implementation plan.

Steps to Construct Data Flow Diagrams

Four steps are commonly used to construct a DFD

 Process should be named and numbered for easy reference. Each

name should be representative of the process.
 The destination of flow is from top to bottom and from left to right.
 When a process is exploded in to lower level details they are numbered.
 The names of data stores, sources and destinations are written in capital
letters.

Rules for constructing a Data Flow Diagram

 Arrows should not cross each other.

 Squares, circles and files must bear names.
 Decomposed data flow squares and circles can have same names.
 Draw all data flow around the outside of the diagram.

DATAFLOW LEVEL:0
DATAFLOW:1