The Generation of Automated Learner Feedback Based on Individual Proficiency Levels

Computer-adaptive tests (CATs) are software applications that adapt the level of difficulty of test questions to the learner’s proficiency level. The CAT prototype introduced here includes a proficiency level estimation based on Item Response Theory and a questions’ database. The questions in the database are classified according to topic area and difficulty level. The level of difficulty estimate comprises expert evaluation based upon Bloom’s taxonomy and users’ performance over time. The output from our CAT prototype is a continuously updated user model that estimates proficiency in each of the domain areas covered in the test. This user model was employed to provide automated feedback for learners in a summative assessment context. The evaluation of our feedback tool by a group of learners suggested that our approach was a valid one, capable of providing useful advice for individual development.