Abstract:

In this current digital age, many things about using technology for teaching have been said. In this sense, Serious Games are gaining ground considering that, besides their technological advantages, they provide something else: fun. This factor increases student attention to the matter they are ‘studying’.
There are many researches that show how Serious Games can improve both teaching methods and student marks in several subjects. The approach presented in this paper is complementary. This work is focused on using Serious Games in order to predict the future performance of students in final exam exercises. Accurately predicting future performance of students lets teachers give customized advice to them.
The approach is undertaken by means of machine learning and data mining techniques, and educational data mining techniques in particular. This techniques are applied to data collected from games played by students. For this purposes, we have developed The Conference Interpreter (CoIn), a Serious Game directed towards interpreting and simultaneous translation in foreign languages.
Finally, the undertaken experiment is described and machine learning/data mining results are presented and discused.

Keywords:

Serious games, machine learning, data mining, student performance, foreign languages.