SMS Spam Detection Using Logistic Regression

This project focuses on detecting spam SMS messages using a Logistic Regression model. By preprocessing the dataset and applying text classification techniques, the project achieved high accuracy in classifying messages as spam or ham.

Project Overview

• Objective: To classify SMS messages as spam or ham using Logistic Regression.
• Dataset: SMS Spam Collection Dataset with 5574 messages (87% ham and 13% spam).
• Model: Logistic Regression, trained using TF-IDF vectorizer for feature extraction.
• Outcome: Achieved an accuracy of 96.59% in identifying spam messages.

Key Files

• data (1).csv: Dataset used for training and testing the model.
• miniprojectanalysis.ipynb: Jupyter notebook with code for data preprocessing, model training, and evaluation.
• miniproject report.docx: Project report summarizing the objectives, preprocessing, and results.
• SMS Spam Detection Using Logistic Regression.pptx: Presentation covering key points and findings of the project.

Results

• Accuracy: 96.59%
• Precision (spam): 0.99
• Recall (spam): 0.75
• F1-score (spam): 0.86

Instructions

1. Open the miniprojectanalysis.ipynb file in Jupyter Notebook to explore the data preprocessing and model training.
2. The dataset (data (1).csv) can be loaded into the notebook for model training and evaluation.

Dependencies

• Python 3.x
• Pandas
• Scikit-learn
• Jupyter Notebook