FOPA-MC: fuzzy multi-criteria group decision making for peer assessment

Massive Open Online Courses are gaining popularity with millions of students enrolled, thousands of courses available and hundreds of learning institutions involved. Due to the high number of students and the relatively small number of tutors, student assessment, especially for complex tasks, is a typical issue of such courses. Thus, peer assessment is becoming increasingly popular to solve such a problem and several approaches have been proposed so far to improve the reliability of its outcomes. Among the most promising, there is fuzzy ordinal peer assessment (FOPA) that adopts models coming from fuzzy set theory and group decision Making. In this paper we propose an extension of FOPA supporting multi-criteria assessment based on rubrics. Students are asked to rank a small number of peer submissions against specified criteria, then provided rankings are transformed in fuzzy preference relations, expanded to obtain missing values and aggregated to estimate final grades. Results obtained are promising if compared to other peer assessment techniques both in the reconstruction of the correct ranking and on the estimation of students’ grades.