Open-source BERT - IMDb Sentiment Analysis Model, Accurately Determine the Positive or Negative Tendency of Movie Reviews

Bert Imdb Model

Developed by philipobiorah

This is a sentiment analysis model fine-tuned based on BERT, specifically designed to analyze sentiment tendencies (positive or negative) in IMDb movie reviews.

Text Classification

Transformers

Supports Multiple LanguagesOpen Source License:MIT #Movie Review Sentiment Analysis #BERT Fine-tuning #High Accuracy

Downloads 341

Release Time : 2/8/2025

Model Overview

The model uses bert-base-uncased as the base model and is fine-tuned on the IMDb movie review dataset, capable of accurately identifying sentiment tendencies in text.

Model Features

High Accuracy

Performs excellently on the IMDb dataset, accurately identifying sentiment tendencies in movie reviews.

Confidence Score

Provides confidence scores for predictions, helping users assess prediction reliability.

Easy Integration

Uses standard Hugging Face Transformers interface, making it easy to integrate into various applications.

Model Capabilities

Text Sentiment Analysis

Movie Review Classification

Sentiment Tendency Prediction

Use Cases

Film Review Analysis

Movie Review Sentiment Analysis

Analyze user reviews on platforms like IMDb to automatically determine sentiment tendencies.

Accurately distinguishes between positive and negative reviews.

Film Evaluation Monitoring

Monitor audience feedback trends for newly released films in real-time.

Provides sentiment tendency statistics.

Market Research

Product Review Analysis

Analyze sentiment in user reviews of film-related products.

Understand consumer preferences and satisfaction.

🚀 BERT IMDb Sentiment Analysis Model

This repository houses a fine - tuned BERT model designed for sentiment analysis on IMDb movie reviews. The model can classify text into either Positive or Negative sentiment, providing valuable insights into movie - goers' opinions.

🚀 Quick Start

You can directly access the live demo of this model at Live Demo.

✨ Features

Accurate Sentiment Classification: Effectively classifies IMDb movie reviews as positive or negative.
Confidence Score: Provides a confidence score for each prediction, indicating the reliability of the classification.

📚 Documentation

📦 Model Details

Property	Details
Model Type	Fine - tuned `bert - base - uncased` for sentiment analysis
Training Data	IMDb Movie Reviews
Task	Sentiment Analysis (Binary Classification)
Labels	`0`: Negative; `1`: Positive

💻 Usage Examples

Basic Usage

from transformers import BertTokenizer, BertForSequenceClassification
import torch

model_name = "philipobiorah/bert-imdb-model"

# Load tokenizer and model
tokenizer = BertTokenizer.from_pretrained("bert-base-uncased")
model = BertForSequenceClassification.from_pretrained(model_name)

# Define function for sentiment prediction with confidence score
def predict_sentiment(text):
    inputs = tokenizer(text, return_tensors="pt", truncation=True, padding=True, max_length=512)
    
    with torch.no_grad():
        logits = model(**inputs).logits
    
    # Convert logits to probabilities
    probabilities = torch.nn.functional.softmax(logits, dim=1)[0]
    
    # Get predicted class (0 = Negative, 1 = Positive)
    sentiment_idx = probabilities.argmax().item()
    confidence = probabilities[sentiment_idx].item() * 100  # Convert to percentage
    
    sentiment_label = "Positive" if sentiment_idx == 1 else "Negative"
    
    return {"sentiment": sentiment_label, "confidence": round(confidence, 2)}

# Test the model
result1 = predict_sentiment("This movie was absolutely fantastic!")
result2 = predict_sentiment("I really disliked this movie, it was terrible.")

print(f"Sentiment: {result1['sentiment']}, Confidence: {result1['confidence']}%")
print(f"Sentiment: {result2['sentiment']}, Confidence: {result2['confidence']}%")

📄 License

This project is released under the MIT license.

Featured Recommended AI Models

Empowering the Future, Your AI Solution Knowledge Base

English 简体中文繁體中文にほんご