📃: Text Classification for Spam Detection

[Avdhesh-Varshney]

🔴 Title : Text Classification for Spam Detection
🔴 Aim : Create a text classification system to detect spam messages using machine learning techniques.
🔴 Brief Explanation :

• Gather a dataset of text messages labeled as spam or not spam.
• Preprocess the text data and extract relevant features.
• Train a machine learning model (such as Naive Bayes, SVM, or logistic regression) to classify messages as spam or not spam.
• Develop an interface where users can input text messages and receive predictions on whether they are spam or not.

Screenshots 📷

N/A

---

✅ To be Mentioned while taking the issue :

• Full name :
• What is your participant role? (Mention the Open Source Program name. Eg. GSSOC, SSOC, JWOC, etc.)

---

Happy Contributing 🚀

All the best. Enjoy your open source journey ahead. 😎

[sid7219]

Full name : Siddharth Gupta
GSSoc'24 Extended

[saniyaahemad12]

Please assign this topic to me

[Avdhesh-Varshney]

@sid7219 @saniyaahemad12 tell me the approach and dataset used for the same?

[ramu-nukavarapu]

Approach:
Dataset : Use the public dataset "SMS spam collection dataset"
Text preprocessing : using libraries like pandas, nltk to tokenizing, lowering, remove stop words and perform stemming or lemmatization.
Feature extraction : extract features using TF-IDF vectorizer
Train the model : for training, use naive bayes (good for classification tasks)
User interface : develop using streamlit components

Name : Ramu
Role : GSSoC contributor

Assign this issue to me, to work on this!

[saniyaahemad12]

Here is the approach for text classification for spam detection
Data Collection: Use a labeled dataset like the SMS Spam Collection dataset.
Data Preprocessing:
Clean text by removing special characters and stopwords.
Tokenize and apply stemming/lemmatization.
Feature Extraction:
Use TF-IDF to convert text into numerical vectors.
Optionally, use Bag of Words model.
Model Selection:
Train models using Naive Bayes, SVM, and Logistic Regression.
Model Training and Testing:
Split data into training/testing sets, apply cross-validation.
Model Evaluation:
Use accuracy, precision, recall, and F1-score to evaluate performance.
Interface Development:
Develop a user interface with Tkinter for input and spam prediction.
If you like the technique please assign this topic to me.

[Avdhesh-Varshney]

@ramu-nukavarapu In PR attach the screenshot of the accuracy of the model during training and testing.

[ramu-nukavarapu]

@Avdhesh-Varshney okay

Add hackotoberfest label as well

[aakashmohole]

i like to solve this issue please assign it to me

Name : Aakash