2019/2020 - 3rd Year, 2nd Semester
Course: Inteligência Artificial (IART) | Artificial Intelligence
Authors: David Silva (daviddias99), Luís Cunha (luispcunha) and Manuel Coutinho (ManelCoutinho)
Description: see bellow
Technologies: Python, SciPy, Pandas, Numpy, PyTorch, Matplotlib
Skills: NLP, sentiment analysis, Machine Learning, supervised learning, neural networks, Tweets, SVM, Naive-Bayes, Perceptron, LSTM, Word embeddings, text-preprocessing
Grade: 19/20
This project used NLP techniques to solve the SemEval-2018’s E-c task. The task's goal was to classify a Tweet as ’neutral or no emotion’ or as one, or more, of eleven given emotions (anger, anticipation, disgust, fear, joy, love, optimism, pessimism, sadness, surprise and trust) that best represent the mental state of the tweeter.
We used NLP techniques to pre-process the data and to classify it according to the given classes such as: Näive-Bayes, Logistic Regression, Deep Learning Model using LTSM Neural Network and Word Embeddings.
For more details on the project see the src/ folder.