harrycool12/Mining-Misconception-in-Mathematics

Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

Mathematical Misconceptions Detector

Overview

This application uses Natural Language Processing (NLP) and machine learning to detect and analyze mathematical misconceptions in student responses. It can identify common misconceptions, help educators understand learning gaps, and provide insights for targeted instruction.

Features

• —Misconception Detection: Analyze text responses to identify common mathematical misconceptions
• —Batch Analysis: Process multiple responses at once for classroom-wide insights
• —Interactive Visualization: View misconception patterns and frequencies
• —Model Training: Ability to train on new data to improve detection accuracy

How to Use

1. 1.Train the Model: Begin by training the model with the included dataset
2. 2.Analyze Responses: Upload a CSV file of student responses for analysis
3. 3.View Results: Review detected misconceptions with highlighted explanations
4. 4.Generate Predictions: Test the model on new data to evaluate its performance

Technical Details

• —Built with Streamlit, scikit-learn, and NLTK
• —Uses TF-IDF vectorization for feature extraction
• —Implements multi-label classification for misconception detection
• —Processes mathematical notation in LaTeX format