💬 Twitter Sentiment Analysis

Twitter Sentiment Analysis is the process of using Python to understand the emotions or opinions expressed in tweets automatically. By analyzing the text, we can classify tweets as positive (1) or negative (0). This helps businesses and researchers track public mood, brand reputation, or reactions to events in real time.

This project includes a trained machine learning model, a user-friendly desktop GUI, and utilizes natural language processing techniques to make sentiment predictions from tweet text input.

---

📌 Overview

• Build a logistic regression model to classify sentiments in tweets.

• Create a graphical interface using Tkinter for user interaction.

• Predict the sentiment of custom tweet inputs (0 = Negative, 1 = Positive).

• Accuracy of trained model: 80%

---

✨ Features

• 🔍 Predict sentiment of custom tweets in real-time.

• 🧠 Trained model with 88% accuracy.

• 📊 Clean and interactive desktop GUI.

• 🎯 Easy to use for non-technical users.

• 📦 Fully open-source and customizable.

---

📁 Dataset

The dataset used is the Sentiment140 dataset, which contains:

• 1.6 million tweets

• Pre-labeled as 0 = Negative and 1 = Positive

• Dataset includes tweet text and metadata

📂 Dataset link: Sentiment140 on Kaggle

• Kaggle Notebook: (https://www.kaggle.com/code/muqaddasejaz/twitter-sentiment-analysis-using-svm)

---

✅ Result

• Model Used: SVM Classifier

• Vectorizer: TF-IDF

• Accuracy Achieved: 80%

• Sample Predictions:

  • "I love this new phone!" → Positive (1)

  • "Worst service ever." → Negative (0)

  • Sentiment Distribution:

    

  • Confusion Matrix:

    

---

🛠 Tools & Technologies

Tool/Library	Purpose
Python	Core programming language
Scikit-learn	Model training (SVM Classifier)
NLTK	Tokenization, preprocessing
TextBlob	Sentiment feature extraction
Tkinter	GUI development
Pandas	Data manipulation
Matplotlib	Visualization
Joblib	Model saving/loading
PIL (Pillow)	Displaying GUI images

---

📸 GUI Preview

• Positive:

• Negative:

  

---

🔗 References

• Sentiment140 Dataset

• https://arxiv.org/pdf/1601.06971

• https://ieeexplore.ieee.org/document/6726818

• https://www.geeksforgeeks.org/python/twitter-sentiment-analysis-using-python/

---

👩‍💻 Author

Muqadas Ejaz

BS Computer Science (AI Specialization)

Machine Learning & Computer Vision Enthusiast

📫 Connect with me on LinkedIn

🌐 GitHub: github.com/muqadasejaz

---

📝 License

This project is licensed under the MIT License.