Open AccessDeep Learning based Sentiment Analysis for Social Media Network
Author(s) -
Dr.R. Murugeswari,
T. M. Sanjeev Kumar,
D. Devaraj,
P. Karthika
Publication year - 2019
Publication title -
international journal of engineering and advanced technology
Language(s) - English
Resource type - Journals
ISSN - 2249-8958
DOI - 10.35940/ijeat.a1098.1291s419
Subject(s) - sentiment analysis , computer science , artificial intelligence , multilayer perceptron , artificial neural network , support vector machine , machine learning , product (mathematics) , process (computing) , representation (politics) , precision and recall , deep learning , perceptron , natural language processing , mathematics , geometry , politics , political science , law , operating system
Sentiment Analysis is the process of identifying opinions expressed in a piece of text. It determines whether the writer's attitude towards a product is positive, negative, or neutral. Sentiment evaluation addresses such need by way of detecting evaluations on the social media textual content. Product evaluations are valuable for upcoming shoppers in supporting them make choices. In recent, deep learning is loom as a powerful manner for fixing sentiment classification troubles. The neural network intrinsically learns a beneficial representation without the efforts of human. This paper presents the overall performance evaluations of deep learning classifiers for big-scale sentiment evaluation. In this system the reviews from the online shopping website called flipkart.com is analyzed and divided as positive, negative and neutral by Multilayer Perceptron (MLP) Neural Network depending on the aspect of the product. The proposed work is simulated by using SPYDER. In our system the accuracy, precision, F-measure and recall is calculated for Multilayer Perceptron (MLP) Neural Network, Random Forest and Support Vector Machine (SVM) algorithm. During comparison Multilayer Perceptron (MLP) Neural Network gives the best accuracy of 99% than other two algorithms.