A Survey On Feature Selection Method For Product Review
V. Senthilkumar, B. Vinoth Kumar · 2021 International Conference on Advancements in Electrical, Electronics, Communication, Computing and Automation (ICAECA) · 2021
The internet becomes a lot more accessible with the help of wireless technology.a great site to learn online, share ideas, and read reviews for the purpose of a product or service. It may be tough to keep track of and comprehend consumer feedback when there are millions of internet reviews for a product or service.Usersatisfaction can be improved by analyzing the sentiment of a huge number of user reviews on e-commerce sites. A discourse analysis, due to the use of official speech, errors and shorter versions of words in short, results in increasing heterogeneity and sparseness, is hard in short texts. Sentiment analysis uses a set of features derived from meaningful words taken from data. A selection of subsets is the strategy for selecting a subset of important characteristics from a big corpus to improve classification accuracy.In machine learning or pattern recognition applications, feature selection approaches allow us to reduce computation time, improve prediction performance, and gain a deeper knowledge of the data. We offer an overview of some of the methods used in the literature in this study. In this study, we used a few feature selection approaches such as the genetic algorithm, Principal Component Analysis, Forest Optimization Algorithm and particle swarm optimization.