On One Approach of Solving Sentiment Analysis Task for Kazakh and Russian Languages Using Deep Learning

摘要

The given research paper describes modern approaches of solving the task of sentiment analysis of the news articles in Kazakh and Russian languages by using deep recurrent neural networks. Particularly, we used Long-Short Term Memory (LSTM) in order to consider long term dependencies of the whole text. Thereby, research shows that good results can be achieved even without knowing linguistic features of particular language. Here we are going to use word embedding (word2vec, GloVes) as the main feature in our machine learning algorithms. The main idea of word embedding is the representations of words with the help of vectors in such manner that semantic relationships between words preserved as basic linear algebra operations.