Student Feedback System using Python and Machine Learning

In today’s education system, it’s important to know how students feel so teachers and schools can improve learning. This Student Feedback System is a web app made with Python and Machine Learning. It takes student feedback and checks if it’s positive, neutral, or negative using sentiment analysis.

Project Overview

In this project, students can give feedback without writing their name. The system then uses machine learning to find out the sentiment — whether the feedback is Positive, Neutral, or Negative.There are different dashboards for students, teachers, and admins, where they can see the feedback results and trends using simple charts.The backend is built using Python and Flask, and it stores data in SQLite. It uses ML models like Naive Bayes and SVM to check feedback, and Matplotlib is used for showing charts. The user interface is made with HTML, CSS, and Bootstrap.

Download New Real Time Projects :-Click here

Key Features

1. Anonymous Feedback Submission

   • Students can submit their feedback securely without revealing personal details.

   • Ensures unbiased responses and encourages honest opinions.

2. Sentiment Analysis Using ML Models

   • Feedback text is processed with machine learning classifiers like Naive Bayes and SVM.

   • Pre-trained on labeled datasets to accurately categorize responses as Positive, Negative, or Neutral.

3. Role-Based Authentication

   • Student Role: Can log in and submit feedback anonymously.

   • Admin Role: Can manage student records, review all submitted feedback, and analyze sentiment trends.

4. Interactive Dashboards

   • Admin dashboard provides data visualizations for quick insights.

   • Includes:

     • Sentiment distribution via pie charts and bar graphs.

     • Total feedback statistics and trends over time.

5. Structured Storage with Database

   • Feedback and user details are stored in a SQLite database for reliability and scalability.

   • Enables easy retrieval, search, and historical analysis of student feedback.

6. Modular Codebase

   • The application follows a clean MVC-style separation of concerns:

     • Models: Machine learning logic for sentiment classification.

     • UI Templates: User-friendly forms and dashboard pages.

     •  

 Technologies Used

Running the Application

To start the server, simply run:

python server.py

This will launch the web application at http://127.0.0.1:5000/.

User Roles and Access

1. Login

Users navigate to the /login endpoint and are directed to their respective dashboards based on their role:

• Student
• Admin

2. Feedback Submission

Students can submit feedback through /feedback, which includes:

• Feedback text
• Teacher/department selection

Once submitted:

• The text is analyzed using a pre-trained ML model.
• Sentiment is classified as:
  • Positive (1)
  • Neutral (0)
  • Negative (-1)
• Data is stored in a CSV file (feedback_data table).

3. Admin Dashboards

Admins can:

• View the total number of feedback submissions
• Analyze sentiment distribution through pie charts
• Read feedback entries along with sentiment scores

Visualizations are dynamically generated using Matplotlib or equivalent.

ML Model Integration

ML models are stored in the models/ folder and used within server.py. For example:

MultinomialNB_stemmed_classifier.pkl

These are loaded to analyze incoming feedback automatically.