Sentiment Analysis based on word vector representation for short comments in Vietnamese language

Word vector representation is a major stage in Natural Language Processing (NLP). It can be applied in various application such as sentiment analysis, text mining, topic detection, document summarization, information retrieval and has an impact to the performance. In literature, different proposed method focus on enhancing word representation model by N-gram, TF-IDF, and word embedding. This paper investigates several word vector representation for Vietnamese sentiment analysis including TF-IDF, Word2Vec, GloVe, and Doc2Vec. The experiment is evaluated on the five common classifiers and two Vietnamese sentiment analysis dataset.