Computer-Assisted Valuation of Descriptive Answers Using Weka with RandomForest Classification

摘要

The main purpose of this system is to reduce the revaluation of copies in the university. Details of how the approach can be used are briefly described in this paper. Moreover, details of the functions used in the approach are also explained. In descriptive examination system, there are a lot of human efforts required and more when revaluation of some copies adds up as an additional task. To reduce extra efforts in valuation, this approach is proposed. It can be used by compiling it with a framework so that non-technical person can also use it, and the approach can be used in real-life systems. However, the proposed method may also be used as 'Computer assisted Manual valuation of illustrative answers' where each answer was first evaluated by computers and then manual valuation; if the difference between manually allocated marks and auto-evaluated marks is higher than the predefined threshold, then an alert will be generated to the human evaluator in order to re-correct and evaluate it again.