Semantic Sentiment Analysis Based on Probabilistic Graphical Models and Recurrent Neural Networks

Abstract

Abstract
Sentiment Analysis is the task of determining the sentiment polarity expressed in textual documents. This can be achieved by using lexical and semantic methods. The purpose of this study is to investigate the use of semantics to perform sentiment analysis based on probabilistic graphical models and recurrent neural networks (RNN). In our empirical evaluation, the classification performance of the graphical models was compared with some traditional machine learning classifiers and a recurrent neural network. The datasets used for the experiments were IMDB movie, Amazon Consumer Product reviews, and Twitter Review datasets. Obtained results from empirical
study show that semantic representation of textual documents using word embeddings in conjunction with longshort term memory (a RNN family) for classification produces better result in determining the polarity expressed in texts. Sentiment Analysis is the task of determining the sentiment polarity expressed in textual documents. This can be achieved by using lexical and semantic methods. The purpose of this study is to investigate the use of semantics to perform sentiment analysis based on probabilistic graphical models and recurrent neural networks (RNN). In our empirical evaluation, the classification performance of the graphical models was compared with some
traditional machine learning classifiers and a recurrent neural network. The datasets used for the experiments were IMDB movie, Amazon Consumer Product reviews, and Twitter Review datasets. Obtained results from empirical study show that semantic representation of textual documents using word embeddings in conjunction with longshort term memory (a RNN family) for classification produces better result in determining the polarity expressed in texts.