Sentiment analysis of a document using deep learning approach and decision trees

• Published in: 2015 Twelve International Conference on Electronics Computer and Computation (ICECCO) pp. 1 - 4
• Main Authors: Zharmagambetov, Arman S., Pak, Alexandr A.
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.09.2015
• Subjects: Classification algorithms; Computational modeling; deep learning; Machine learning; Motion pictures; NLP; Semantics; Sentiment analysis; Text categorization; text classification
• DOI: 10.1109/ICECCO.2015.7416902

The given paper describes modern approach to the task of sentiment analysis of movie reviews by using deep learning recurrent neural networks and decision trees. These methods are based on statistical models, which are in a nutshell of machine learning algorithms. The fertile area of research is the application of Google's algorithm Word2Vec presented by Tomas Mikolov, Kai Chen, Greg Corrado and Jeffrey Dean in 2013. The main idea of Word2Vec is the representations of words with the help of vectors in such manner that semantic relationships between words preserved as basic linear algebra operations. The extra advantage of the mentioned algorithm above the alternatives is computational efficiency. This paper focuses on using Word2Vec model for text classification by their sentiment type.