Predicting Polarities of Tweets by Composing Word Embeddings with Long Short-Term Memory

Key Points

• This study aims to enhance the accuracy of predicting the sentiment polarity of tweets.
• Utilized word embeddings for feature representation of tweets.
• Implemented Long Short-Term Memory (LSTM) networks for classification.
• Analyzed the composition of embeddings to improve sentiment detection.
• Achieved a significant improvement in polarity classification accuracy.
• Demonstrated robust performance in processing sequential data from tweets.