Mining user satisfaction decision stages from online reviews is helpful for understanding user preferences and conducting user-centered product improvements. Therefore, this study develops a two-stage nonlinear user satisfaction decision model (USDM). First, we use word2vec technology and lexicon-based sentiment analysis to mine the sentiment polarity of each product attribute in the reviews. Then, we develop KANO mapping rules using utility functions to classify consumer preferences based on attribute importance. Based on this, a two-stage nonlinear USDM is developed to describe post-purchase evaluation behavior. In the first non-compensatory stage, consumers determine their initial satisfaction level based on the performance of basic attributes. If the performance of these attributes is poor, it is almost impossible for users to be satisfied. In the compensatory stage, the performance of the remaining attributes collectively affects final satisfaction through participation in user utility calculation. With the use of reviews from JD.com, we develop a genetic algorithm to determine feasible solutions for the USDM and verify its validity and robustness. The USDM is proven to be effective in predicting user satisfaction compared to other classic models and machine learning algorithms. This study provides a universal pattern for user satisfaction decisions and extends the study on preference analysis.

Objective: The aim is to investigate the determinants and mechanisms that influence user's highly sensitive privacy disclosure intention (HSPDI) in home intelligent health service system (HIHSS).Methods: This study improves the privacy calculus theory by considering the influence of service providers’ trust enhancement mechanism besides benefit and risk factors and investigates their impact on users’ HSPDIs. This study takes perceived valence and perceived security as the trade-off result among perceived benefits, perceived risks, financial trust enhancement mechanism, and the technical trust enhancement mechanism and suggests that perceived valence and perceived security further affect users’ HSPDI in HIHSS. Moreover, the common and differential effects of the perceived justice of privacy violation compensation (PJOPVC) and the perceived effectiveness of privacy protection technologies (PEOPPTs) are studied. The structural equation model is used to analyze 204 valid samples to test the proposed model.Results: The results show that perceived benefits and perceived risks are important predictors of perceived valence and perceived security, and further affect users’ HSPDI. We find PJOPVC has a greater impact on perceived valence while PEOPPT has a greater impact on perceived security.Conclusions: We recommend that the HSPDI of users with low perceived valence can be improved by providing privacy violation compensation while the HSPDI of users with low perceived security can be enhanced by popularizing relevant knowledge of privacy protection technologies.