Emojify Text is a web application built using Flask and Keras that predicts and appends relevant emojis to the input text. It utilizes a Long Short-Term Memory (LSTM) neural network trained on a dataset of text samples paired with emoji labels.
- Preprocessing and tokenization of text data.
- Training an LSTM neural network model.
- Building a web interface using Flask.
- Predicting emojis for user-input text.
- Python
- Flask
- Keras
- TensorFlow
- Pandas
- NumPy
- Python 3.x
- pip (Python package manager)
-
Clone the repository:
git clone https://github.com/Priyanshuparth/Emojify_text.git
-
Install the required Python packages:
pip install -r requirements.txt
-
Download the pre-trained GloVe word embeddings:
- Download glove.6B.100d.txt from here
- Place the file in the project directory.
- Run the Flask application:
python app.py
- Open a web browser and go to http://localhost:5000 to access the application.
- Enter your text in the input field and submit. The application will predict and display the corresponding emoji.
The LSTM model architecture consists of an embedding layer followed by two LSTM layers and a dense layer with softmax activation. The model is trained using categorical cross-entropy loss and optimized using the Adam optimizer.
The dataset used for training consists of text samples paired with emoji labels. The dataset is preprocessed and tokenized before training the model.
The GloVe word embeddings used in this project were trained by the Stanford NLP Group.
This project is licensed under the MIT License.