Personalised Automated Assessments

Consider a person who needs to assess a large amount of information. For instance, think of a teacher of a massive open online course with thousands of enrolled students, or a senior program committee member in a large conference who needs to decide what are the final marks of reviewed papers, or a buyer in an e-commerce scenario who needs to build up her opinion about products. When assessing a large number of objects, sometimes it is simply unfeasible to evaluate them all and very often one needs to rely on the opinions of others. In this paper, we provide a model that uses peer assessments (assessments made by others) in an online community to approximate the assessments that a particular member of the community would generate given the occasion to do so (e.g. the tutor, the SPC member or the buyer--we refer to this person as the leader). Furthermore, we provide a measure of the uncertainty of the computed assessments and a ranking of the objects that should be assessed next. The model, although inspired by human societies is thought to be used in the organisation of agent communities.