SExplanatory and Predictive Modeling of Cybersecurity Behaviors using Protection Motivation Theory

Abstract

Context: Protection motivation theory (PMT) is the most frequently used theory in understanding cyber security behaviors. However, most studies have used a cross-sectional design with symmetrical analysis techniques such as structure equation modeling (SEM) and regression. A data-driven approach, such as predictive modeling, is lacking and can potentially evaluate and validate the predictive power of PMT for cybersecurity behaviors. Objective: The objective of this study is to assess the explanatory and predictive power of PMT for cyber security behaviors related to computers and smartphone. Method: An online survey was employed to collect data from 1027 participants. The relationship of security behaviors with threat appraisal (severity and vulnerability) and coping appraisal (response efficacy, self-efficacy and response cost) components were tested via explanatory and predictive modeling. Explanatory modelling was employed via SEM, whereas three machine learning algorithms, namely Decision Tree (DT), Support Vector Machine (SVM), and K Nearest Neighbor (KNN) were used for predictive modeling. Wrapper feature selection was employed to understand the most important factors of PMT in predictive modeling. Results: The results revealed that the threat severity from the threat appraisal component of PMT significantly influenced computer security and smartphone security behaviors. From the coping appraisal, response efficacy and self-efficacy significantly influenced computer and smartphone security behaviors. The ML analysis showed that the highest predictive power of PMT for computer security was 76% and for smartphone security 68% by KNN algorithm. The wrapper feature selection approach revealed that the most important features in predicting security behaviours are self-efficacy, response efficacy and intention to secure devices. Thus, the findings indicate the complementarity of the cross-sectional and data driven methods.