Challis , D. (2005). Committing to quality learning through adaptive online. Assessment & Evaluation in Higher Education V30 (5), pp. 519–527.

Adaptation has become a hot topic in recent years. From e-business to e-education, the system was designed to have certain intelligence to customize its services to suit individual need. For instance, amazon.com provides features like recommended products; Google users are able to personalize their own Google home page. Adaptation has been widely employed in e-business systems. However when it comes to education, the concept is extremely different. A business can make profit by recommend one suitable product to customers out of ten inaccurate recommendations. But in education, it is dangerous to provide learners inaccurate instructions just because based on predefined rules, this instruction may be suitable for learners in his/her level.

Adaptive assessment, in the journal articles discussed, can be seen as part of the adaptive system (which provide adaptive instruction as well as adaptive assessment) or can be used separately from non-adaptable teaching instructions. The assessment may be used either formative assessment or summative assessment and such assessment has the following features:

- User level is constantly established via the assessment.
- Assessment becomes more difficult/complex or easier, depending on the demonstrated level of answer.
- Users can specify an entry level and the sequencing of the test items will adapt to it.
- Remediation can be provided through embedded feedback.
- Assistance can be offered without drawing on lecturers’ time.
- The score is derived from the level of difficulty of the questions answered correctly.

Most online assessments are multiple choice questions because they are easy to be developed and grated. With current technology, short answers or essay type questions are almost impossible to be marked without involving instructors. The issues here is that without human involvement, simply based on pre-defined rules and difficulty level of questions, how system can accurately determine users’ level. For instance, when a student answered a math question (multiple choice questions) incorrectly, there are many possible explanations. The student may do the wrong calculation; the student may not know the formula at all or the student may apply the incorrect formula. Different assistance should be provided to the student in the above three situations. It is a challenge for system to diagnosis learner’s error based on correct or incorrect user feedback in the first place; and then the following adaptation process may be inappropriate if the first step is already inaccurate.

Both adaptive instruction and adaptive assessment are good concept but there is a long way to go to make such adaptation useful in education area.