Sentiment Analysis based optimization approach
Anita Gehlot, Rajesh Singh, Abhishek Joshi · 2022
Sentiment analysis is a method that uses peer-reviewed literature to address issues from a variety of specialised scientific viewpoints. It's crucial to read reviews before purchasing a product so that you're aware of the benefits and drawbacks of the items you want to use; for example, you may learn whether or not a certain cosmetic brand is of a usable quality by reading reviews of the product. In order to make an informed decision about a cosmetics purchase, shoppers should read reviews and testimonials from other customers who have tried the product in question. It's clear that people are becoming more wary of review sites due to the sheer volume of reviews available. The reviews stop being useful at some point. So that readers may locate reliable product comparisons quickly, the writers categorise using both positive and negative classifications. Support Vector Machine (SVM) and Nave Bayes (NB) algorithms may both benefit from the adoption of Particle Swarm Optimization (PSO) with Genetic Algorithm (GA) optimization, resulting in more accurate and optimum solutions to the review categorization issue. In a head-to-head comparison using this data set, an SVM algorithm achieves an accuracy of 89.20% and an area under the curve (AUC) of 0.973, whereas an SVM based on PSO achieves an accuracy of 94.60% and an AUC of 0.985. Testing the data using the NB algorithm yielded an accuracy of 88.50% and an AUC of 0.536; next, the accuracy was compared to that of the PSO-based NB method, which was 0.692. These numbers show that PSO optimization may be used to increase precision and provide better answers.