Adapting the automatic assessment of free-text answers to the students

In this paper, we present the first approach in the field of Computer Assisted Assessment (CAA) of students' free-text answers to model the student profiles. This approach has been implemented in a new version of Atenea, a system able to automatically assess students' short answers. The system has been improved so that it is now able to take into account the students' preferences and personal features to adapt not only the assessment process but also to personalize the appearance of the interface. In particular, it is now able to accept students’ answers written in Spanish or in English indistinctly, by means of Machine Translation. Moreover, we have observed that Atenea’s performance does not decrease drastically when combined with automatic translation, provided that the translation does not reduce greatly the variability in the vocabulary.