Using BERT to predict emotional classification labels of Tweets
Exploratory Data Analysis and Preprocessing
Training/Validation Split
Loading Tokenizer and Encoding the Data
Setting up BERT Pretrained Model
Creating Data Loaders
Setting Up Optimizer and Scheduler
Defining Performance Metrics
Creating the Training Loop
Loading and Evaluating the Model
The dataset used for this project was the SMILE Twitter dataset.
Wang, Bo; Tsakalidis, Adam; Liakata, Maria; Zubiaga, Arkaitz; Procter, Rob; Jensen, Eric (2016): SMILE Twitter Emotion dataset. figshare. Dataset.
https://doi.org/10.6084/m9.figshare.3187909.v2
Run the main.py file's code in Google colab in order to train the model using GPU.
Make sure to include the SMILE dataset in colab.