https://github.com/ahmed-hassan-ai/nlp-sentiment-analysis

Sentiment Analysis
https://github.com/ahmed-hassan-ai/nlp-sentiment-analysis

dropout keras lstm matplotlib numpy pandas regularization seaborn

Last synced: 30 days ago
JSON representation

Sentiment Analysis

• Host: GitHub
• URL: https://github.com/ahmed-hassan-ai/nlp-sentiment-analysis
• Owner: Ahmed-hassan-AI
• Created: 2024-11-13T11:00:52.000Z (3 months ago)
• Default Branch: main
• Last Pushed: 2024-11-13T11:39:02.000Z (3 months ago)
• Last Synced: 2024-11-13T12:31:04.372Z (3 months ago)
• Topics: dropout, keras, lstm, matplotlib, numpy, pandas, regularization, seaborn
• Language: Jupyter Notebook
• Homepage:
• Size: 43.9 KB
• Stars: 1
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# sentiment Analysis

## 📃 DataSet 

size : 50000 * 2 

nagative data Size : 25000 

Postive data Size : 25000 

count Null Values : 0

## 🛠 Lib

- pandas

 

- numpy

- scikit-learn

- matplotlib

- seaborn

- keras

## ✒ preprocessing

- Replace Postive and Nagative to 0 and 1

- tokeniztion

## model 

### 🧱 Architecture 

1 • embedding Layer output is 128 dim  

2 • Lstm Layer from 64 cell 

3 • Lstm Layer from 32 cell

4 • Dence from 1 cell and sigmoid activtion function

### traing setting

- regurilazition dropout 50%

- optimizer = adam

- epochs = 5

- batch size = 5 

## 🔻 model evaluate  ≌ 90 %