| Summary: | Abstract The present study focuses on the integration of an automatic question generation (AQG) system and a computerised adaptive test (CAT). We conducted two experiments. In the first experiment, we administered sets of questions to English learners to gather their responses. We further used their responses in the second experiment, which is a simulation-based experiment of the AQG and CAT integration. We proposed a method to integrate them with a predetermined item difficulty that enables to integrate AQG and CAT without administering the items in a pretesting. The result showed that all CAT simulations performed better than the baseline, a linear test, in estimating the test taker’s true proficiency.
|
|---|