This project aims to build a sentiment analysis model that automatically classifies textual data—such as reviews and social media posts—into positive, negative, or neutral categories. The analysis is useful for understanding public opinion, enhancing customer experience, and identifying sentiment trends over time.
- Automatically classify text into sentiment categories.
- Understand public opinion on topics, products, or brands.
- Improve customer experience by analyzing feedback.
- Track sentiment trends to guide business decisions and marketing strategies.
The dataset is stored in a CSV file: sentimentdataset.csv.
| Column | Description |
|---|---|
ID |
Unique identifier for each entry |
Text |
The textual content (e.g., reviews or posts) |
Source |
Origin of the text (e.g., website, Twitter) |
Topic |
Category or product/brand reference |
Label |
Sentiment label (positive, negative, neutral) |
Dataset URL: Click to Access
- Lowercasing text
- Removing punctuation and stopwords
- Text normalization (e.g., expanding slang)
- Stemming or lemmatization
- Bag-of-Words
- TF-IDF (Term Frequency–Inverse Document Frequency)
- Word Embeddings (e.g., Word2Vec, GloVe)
Choose from the following algorithms:
- Naive Bayes
- Support Vector Machines (SVM)
- Logistic Regression
- Recurrent Neural Networks (RNN) or Long Short-Term Memory (LSTM)
- Accuracy
- Precision
- Recall
- F1-Score
| Name | Github Link |
|---|---|
| Tasneem Mohamed Ahmed Mohamed | https://github.com/Tasneem357Mohamed |
| Esraa Saied Maray | https://github.com/esraasaidmaray |
| Toka Karam Abdelmageed Madany | https://github.com/Toka136 |
| Bsmala Tarek Kamal Khalil Elbagoury | https://github.com/Bsmalatarek |
| Amira Mostafa Haroon Abdelwahab | https://github.com/amira468 |
| Omnia Salah Mahmoud Hamed | https://github.com/Matata2020 |