Sentiment Analysis of Social and Topic Context UsingMachine Learning Techniques
Ratna Patil, Sonia Arora · Journal of Critical Reviews · 2020
Sentiment Analysis could be a new area in research and is beneficial in many other fields. In the present time, a large amount of textual data is collected using surveys, comments, and reviews online. All the collected data are employed to enhance the items and services provided by both public and private organizations around the world. This Paper introduces a sentiment analysis of social and context reviews using feature-based opinion mining and supervised machine learning. The Sentiment Analysis techniques are to function on a series of expressions for a given item that supported the product quality, and item features. Sentiment analysis is additionally called Opinion mining because of the significant volume of opinion. Analyzing customer opinion is extremely important to rate the items. To automate rate the opinions within the type of unstructured data is been a challenging problem today. Social context and topic context are combined by the Laplacian matrix of the graph built by these contexts and Laplacian regularization is added into the microblog sentiment analysis model. Experimental results on two real Twitter data sets demonstrate that our proposed model can outperform baseline methods consistently and significantly. Various topics beyond item reviews like online shopping, stock markets, elections, disasters, medicine, software engineering, and Cyberbullying extend the utilization of sentiment analysis.