OPINION MINING FOR USER EXPERIENCE EVALUATION MODEL USING BAYESIAN ESTIMATION OF MARKOV CHAIN MONTE CARLO TECHNIQUE

Abstract

Online marketing is based on digital technology, including e-commerce marketing, content automation, social media marketing, and e-mail direct marketing provides advanced technology in the digital marketing system. User experience is one of the common strategies for product success. The previous research work provides user experience improvement in ordinary marketing. The proposed research work evaluates the major issues of analyzing user experience based on website data. The extraction process focuses on interfacing Google Analytics through the respective web stores. Google analytics helps to understand the behavior component groups of user’s struggle. Presented cumulative prospect theories in which user involvement is perceived from the perspective of strategy procedure of two various model images. Investigate the affective states on user experience dataset evaluation through affective characteristics involved in user experience design. Furthermore, we study the account for multiple data sets of uncertainties and improve a hierarchical database Prior Probability and Posterior Probability. Presented advanced Markov chain Monte Carlo technique for characteristics evaluation fewer than four affective states by using image-processing methods. A result concludes impacts by mapping its parameters in the perceived user experience function. Concentrate on the central tendency of the data, idiosyncratic user experience models can be built in the estimation process. Keywords: User experience model; opinion mining; Bayesian Function; MCMC; Google Analytics data;