saubhagya122k4/bert-sentiment-analysis

BERT Sentiment Analysis 🚀

This is a fine-tuned BERT model (bert-base-uncased) for sentiment analysis on the IMDb movie review dataset. The model classifies text into:

• ✅ Positive
• ❌ Negative

---

🧠 Model Details

• Base Model: bert-base-uncased
• Dataset: IMDb (via Hugging Face Datasets)
• Classes: Binary classification (0: Positive, 1: Negative)
• Framework: PyTorch
• Training: Fine-tuned using Hugging Face Transformers and Datasets on GPU

---

📥 How to Use

You can use this model directly with 🤗 transformers:

from transformers import BertTokenizer, BertForSequenceClassification
import torch
import torch.nn.functional as F

model_name = "saubhagya122k4/bert-sentiment-analysis"

tokenizer = BertTokenizer.from_pretrained(model_name)
model = BertForSequenceClassification.from_pretrained(model_name)
model.eval()

text = "This movie was fantastic! I really enjoyed it."

inputs = tokenizer(text, return_tensors="pt", truncation=True, padding=True, max_length=70)

with torch.no_grad():
    outputs = model(**inputs)
    probs = F.softmax(outputs.logits, dim=1)
    predicted = torch.argmax(probs, dim=1).item()

labels = {0: "Positive", 1: "Negative"}
print(f"Sentiment: {labels[predicted]}")

---

📊 Performance

• Accuracy: ~93% on test set
• Tokenizer: bert-base-uncased
• Sequence Length: 70 tokens

---

🛠 Training & Fine-tuning

• Notebook: View on Kaggle
• Framework: PyTorch + Hugging Face Transformers
• Batch Size: 16
• Epochs: 3
• Optimizer: AdamW

---

📦 Use Cases

• Movie review classification
• Customer feedback analysis
• Product sentiment detection

---

🧾 License

This model is available for public use under the Apache 2.0.

---

🙋‍♂️ Author

Saubhagya Vishwakarma 📧 saubhagya.v@simformsolutions.com 🔗 GitHub