Empirical Comparative Study of Wearable Service Trust Based on User Clustering

Users of wearable services are different in age, occupation, income, education, personality, values and lifestyle, which also determine their different consumption patterns. Therefore, for the trust of wearable services, the influencing factors or strength may not be the same for different users. This article starts with the resource and motivation dimensions of VALSTM model, and the clustering model and questionnaire scale for consumers of wearable services were constructed. And then the users and potential users of wearable service are clustered by an improved clustering algorithm based on adaptive chaotic particle swarm optimization. Through clustering analysis of 535 valid questionnaires, users are grouped into three types of consumers with different lifestyles, respectively named: trend-following users, fashion-leading users and economic-rational users. Finally, this paper analyzes and compares the trust subgroup models of three clusters, and draws some conclusions.

Empirical Comparative Study of Wearable Service Trust Based on User Clustering

Users of wearable services are different in age, occupation, income, education, personality, values and lifestyle, which also determine their different consumption patterns. Therefore, for the trust of wearable services, the influencing factors or strength may not be the same for different users. This article starts with the resource and motivation dimensions of VALSTM model, and the clustering model and questionnaire scale for consumers of wearable services were constructed. And then the users and potential users of wearable service are clustered by an improved clustering algorithm based on adaptive chaotic particle swarm optimization. Through clustering analysis of 535 valid questionnaires, users are grouped into three types of consumers with different lifestyles, respectively named: trend-following users, fashion-leading users and economic-rational users. Finally, this paper analyzes and compares the trust subgroup models of three clusters, and draws some conclusions.