Comparative Analysis of Using Word Embedding in Deep Learning for Text Classification

A group of theory-driven computing techniques known as natural language processing (NLP) are used to interpret and represent human discourse automatically. From part-of-speech (POS) parsing tagging machine translation dialogue systems, NLP enables computers carry out various language-related activities at all levels. In this research, we compared word embedding FastText GloVe, which for text representation. This study aims evaluate compare the effectiveness in classification using LSTM (Long Short-Term Memory). The research stages start with dataset collection, pre-processing, embedding, split data, last is deep learning techniques. According results experiments, when glove technique it seems that superior, accuracy obtained reaches 90%. number epochs did not significantly improve model GloVe FastText. It can be concluded superior technique.