BUSEM at SemEval-2017 Task 4A Sentiment Analysis with Word Embedding and Long Short Term Memory RNN Approaches (original) (raw)

This paper presents a dual approach for the SemEval-2017 Task 4A on sentiment analysis of Twitter messages, focusing primarily on message polarity classification. The first approach employs word embeddings in conjunction with traditional machine learning classifiers such as SVM, Random Forest, and Naive Bayes. The second approach utilizes Long Short-Term Memory (LSTM) networks, processing word indexes as sequences for input. The methodologies, system descriptions, and performance evaluation of both approaches are detailed, emphasizing the significance of optimal parameter selection in the word embedding process.