Analyzing superstars’ power using support vector machines

Abstract

The main objective of this paper is to explain the influence that superstars have over spectators. The most significant contributions in the field of persuasion are discussed. This theoretical framework suggests some hypotheses that are tested using the data of an empirical study based on a survey of moviegoers. Support vector machine (SVM) is used for data analysis and pattern discovery. The SVM prediction capacity is benchmarked against that from a linear regression and multinomial logit. Results show that the SVM has considerable promise for analyzing spectators’ behavior. The results of this analysis allow us to extract some significant conclusions and implications for the process of creating and maintaining the power of a superstar