US researchers have developed a new artificial intelligence (AI) model that can predict how students' need of academic help by evaluating their performance through video games.
The model makes use of a concept called multi-task learning, and could be used to improve both teaching and learning processes.
Jonathan Rowe, research in North Carolina State University's Center for Educational Informatics (CEI), said: "The new model is able to predict whether a student would answer each question on a test correctly, based on the student's behavior while playing an educational game called Crystal Island."
The research team said the new model could be used to notify teachers when a student needs more academic attention, as well as improving teaching methods in classrooms, the German News Agency reported.
