A deep learning project for sentiment analysis on tweets, classifying them into positive, negative, or neutral sentiments.
MIT License
This project is a sentiment analysis model applied to tweets. It uses machine learning and natural language processing (NLP) techniques to classify the sentiment of tweets into three categories: positive, negative, and neutral. The project demonstrates the use of various preprocessing steps, TF-IDF vectorization, and a deep learning model built with TensorFlow and Keras.
Sentiment analysis is a key aspect of NLP that involves determining the sentiment expressed in a piece of text. This project leverages the power of deep learning and TF-IDF vectorization to perform sentiment analysis on a dataset of tweets.
The model used in this project is a sequential neural network with the following layers:
We have an image depicting a dataframe and a list of features. We will utilize the 'text' feature as input and consider the 'sentiment' feature as our target variable. Our goal is to predict the likelihood of a text being categorized as positive, negative, or neutral.
The data preprocessing pipeline includes:
The model is trained using the following configuration:
The performance of the model is evaluated using accuracy and loss plots. The final trained model is able to classify tweet sentiments with a reasonable accuracy.
To run this project locally, follow these steps:
git clone https://github.com/Vidit-Kushwaha/Tweet-Sentimental-Analysis.git
cd Tweet-Sentimental-Analysis
jupyter notebook Sentiment_Analysis_on_Tweets.ipynb
Train the model: Follow the steps in the notebook to preprocess the data, train the model, and visualize the results.
We welcome contributions! Whether you're a seasoned developer or a curious enthusiast, there are ways to get involved:
You can follow standard python contribution guidelines.
This project is licensed under the MIT License. See the LICENSE file for details.