Opinion mining for user experience evaluation model using kernel-naive bayes classification algorithm

User experience evaluation approach is the major key to adapt the new trends and technology. The product launch is based on the various opinions of users and availability of product. The first impression about the product makes successful sales, which is analysed with UX (User eXperience) design. Before developing / launching the product, have to evaluate the user experience model by online sources. The opinion/sentimental analysis are the way to capture the people’s opinion about the product. Rating, page session, website page views, and number of buyers or users are evaluated as a graph model and predict the requirement of the product. This process makes the product’s benefits. The previous work utilizes the Markov Chain Monte Carlo (MCMC) Method to model the UX design. In this proposed research work, the opinion mining approach is used to get the dataset from Google analytics. This dataset is model using Kernel based Naïve Bayes Classification algorithm and the prior & posterior probability is calculated by MCMC (Markov Chain Monte Carlo) techniques. Classification approach takes the training and testing data. Here the confusion matrix is used to create the UX evaluation model’s accuracy. By this proposed algorithm, it summarized the positive and negative opinion then we can calculate the accuracy of the system and it easily identifies the user opinion. This proposed UX design model improves the result as compared to the previous MCMC method. The data mining based sentimental classification is done with the help of MATLAB 2018a tool.