Skip to content

Ricky2054/Auto_Evaluazer

Repository files navigation

Auto_Evaluazer

Description

Automatic Long Answer Evaluation Model- It allows users to input a question and a model answer, alongside student responses. The model meticulously grades the provided answers by comparing them to the model answer, leveraging advanced techniques such as sentiment analysis, word embeddings, and context matching.

System Architechture

system_architecture

Instructions for using the app:

Make sure that you have python version 3.11.5

Step 1: Create virtual environment,activate it and install requirements, by executing the following commands in the terminal:

python -m venv myenv
myenv\Scripts\activate
pip install -r requirements.txt

Step 2: Make sure that your main python file is named as "app.py"

Step 3: Run the "save_model.ipynb" and make sure that you have selected your 'myenv' as kernel and install the necessary package i.e, ipykernel

To run the application write the following command in the terminal

python app.py

then go to port "http://127.0.0.1:5000" for running the application in the localserver

*In addition to this project we are have created a viva checker version of the system that automatically conducts and evaluates viva Q&A also we are working on a plagarism checker and a code checker addon to our system and that is to come soon as it is in testing phase....

Authors

About

Auto_Evaluazer: NLP-powered system for automatic answer evaluation with ~90% correlation to human grading, providing real-time semantic analysis and contextual relevance checks. Built an interactive dashboard for detailed grading analytics, integrated with AI-text detection and viva-taking features.

Topics

Resources

Stars

Watchers

Forks

Packages

 
 
 

Contributors