Developed and evaluated deep learning models to determine the sentiment attached to a sequence of input texts.
- Implemented various deep learning models, including recurrent neural networks (RNNs), long short-term memory networks (LSTMs), and transformer-based models, to analyze and classify the sentiment of text sequences.
- Collected and pre-processed text data, ensuring it was appropriately formatted and tokenized for input into the models.
- Trained the models on labeled datasets, utilizing techniques such as word embeddings and attention mechanisms to enhance performance.
- Conducted a comparative analysis of the model’s performance based on key metrics, such as precision, recall, and F1-score.
- Transformers outperformed the rest in terms of performance in detecting sentiments and also in terms of representing rare words.