Skip to content

Latest commit

 

History

History
35 lines (20 loc) · 1.85 KB

README.md

File metadata and controls

35 lines (20 loc) · 1.85 KB
Raw

IMDB Reviews Sentiment Analysis with LSTM

This Notebook contains code for sentiment analysis on IMDB movie reviews using Long Short-Term Memory (LSTM) neural networks. Sentiment analysis aims to determine the sentiment expressed in a piece of text, whether it's positive, negative, or neutral. In this project, we focus on classifying IMDB movie reviews as either positive or negative.

Overview

  • IMDB Dataset: The dataset used in this project consists of 50,000 IMDB movie reviews, evenly split into 25k reviews for training and 25k for testing. Each review is labeled as either positive or negative.

  • LSTM: Long Short-Term Memory Networks are a type of recurrent neural network (RNN) architecture capable of learning long-term dependencies in sequential data. They are particularly well-suited for tasks involving sequences like text data.

Getting Started

To run the notebook, follow these steps:

  1. Clone the Repository: Clone this GitHub repository to your local machine.

    git clone https://github.com/your_username/your_repository.git

  2. Install Dependencies: Make sure you have all the required dependencies installed. You can install them using pip:

    pip install -r requirements.txt

Model Performance

The model's performance is evaluated using various metrics such as accuracy, precision, recall, and F1-score on the test dataset. These metrics provide insights into how well the LSTM model is able to classify positive and negative reviews.

Conclusion

Sentiment analysis is a powerful tool for understanding the opinions and emotions expressed in textual data. In this project, we demonstrate how LSTM neural networks can be used for sentiment analysis on IMDB movie reviews. By leveraging deep learning techniques, we achieve competitive performance in classifying sentiment polarity.