Supplement to "A Decade of DiagnosisTM" by T.M. Stewart, Massey University, New Zealand. ISPP - Instructional Technology Symposium (on-line). May 15th-June 30th. 2001.
How does DIAGNOSIS work?
Contrary to what the name might suggest, DIAGNOSIS is not an expert system. These systems embody the knowledge and rules of an expert. As a teaching tool, tutors may get students to use an expert system to assist in the diagnosis of a disease. The students feed the expert system the relevant observations, then look over its shoulder as it offers a diagnosis. The system may explain why it came to a particular conclusion and in that way students learn something about the diagnostic process.
DIAGNOSIS is the reverse of an expert system. It assumes students are the experts and provides them with simulated observations of a plant problem. The students need to come up with the diagnosis themselves. Therefore the students, not the machine, carry out the interpretation and gathering of information. The software simply provides a problem-solving scenario; a sort of virtual reality they can work in. It uses the metaphor of the computer "adventure game" (Zork, Collosus Cave etc.). In such games, common in the 1970's and 1980's, players moved from room to room, inspecting objects and clues and drawing conclusions, which could then enable them to progress further. A lot of thinking and deduction was involved. These same mental tasks also occur in trying to solve an unknown plant problem.
Figure 1. Scenario Screen Shot from the almost-completed Version 3.
The core of DIAGNOSIS is the teacher-constructed scenario. The scenario presents students with a problem (Fig 1). It may be wilting plants in a potato field, disfigured fruit in an apple orchard or yellow leaves on wheat plants. The students are dropped into this problem, usually accompanied by a grower, who can answer questions on management and the history of the problem. The student must then interrogate the scenario, making observations of the plant and the environment, checking equipment and asking the grower questions. Students can collect objects such as plant parts, weeds and soil and take them to the lab for "forensics". Here they can gather further observations, look up weather information, try to extract the causal organisms and/or conduct a number of tests. Once students feel they have enough information to make a diagnosis, they type this into the computer, along with a justification and recommendation. Students can then be told the answer and given immediate feedback, or (more commonly) the student input will be extracted later by their teacher and graded.
Scenarios then, are the "data" used by the DIAGNOSIS program. The software provides a "builder" for teachers, where scenarios can be constructed or altered to suit. A scenario "player" program then presents the problems to students. Scenarios should reflect reality and all its ambiguities, and include situations where the solution is not clear cut They should encourage some real detective work on behalf of the learner. They are best written with the aid of extension personnel, if the teacher is not actively involved in extension work.
Scenarios can incorporate whatever degree of difficulty the teacher feels appropriate for the course. Teachers can make interpretations for students or leave interpretation up to them. For example, if students send away samples for nutrient analysis, the scenario may return the results saying "the nutrient levels appear OK" or alternatively provide a list of values for each nutrient. In the former case, the teacher (or whoever built the scenario) has done the interpretation for the student while the latter requires them to understand the significance of the figures.