A service-oriented architecture for student modeling in peer assessment environments

Abstract

Peer assessment functionalities are provided in several Learning Management Systems; data coming from the peer evaluation sessions could be used for automated or semi-automated grading, for the management of student modeling, and for providing the teacher with feedback about the learners. Various models for the representation of peer assessment data have been proposed in the literature. In this paper we build on the availability of such a model based on Bayesian Networks, and introduce: (1) a web service capable of representing data coming from peer evaluation sessions, in which student modeling is based on learners’ Competence and Assessment capability features; (2) a protocol of communication, and the design of a related API, making the service available, i.e., allowing the exchange of data between the web service and the LMS supporting the peer assessment sessions; (3) a working example of using this API in the Moodle LMS, by means of enhancing the existing Workshop plugin.