Predicting trustworthiness behavior to enhance security in on-line assessment

(c) 2014 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other users, including reprinting/ republishing this material for advertising or promotional purposes, creating new collective works for resale or redistribution to servers or lists, or reuse of any copyrighted components of this work in other works.Over the last decade, information security has been considered a key issue in e-Learning design. Although security requirements can be met with advanced technological approaches and these solutions offer feasible methods in many e-Learning scenarios, on-line assessment activities usually show specific issues that cannot be solved with technology alone. In addition, security vulnerabilities in on-line assessment impede the development of an overall model devoted to manage secure on-line assessment. In this paper, we propose an innovative approach to enhance technological security solutions with trustworthiness. To this end, we endow previous trustworthiness models with prediction features by composing trustworthiness modeling and assessment, normalization methods, history sequences, and neural network-based approaches. In order to validate our approach, we present a peer-to-peer on-line assessment model carried out in a real online course.Peer Reviewe