Determination of Bloom´s cognitive level of question items using artificial neural network

We propose a classification model for the cognitive level of question items in examinations based on Bloom´s taxonomy. The model implements the artificial neural network approach, which is trained using the scaled conjugate gradient learning algorithm. Several data preprocessing techniques such as word extraction, stop word removal, stemming, and vector representation are applied to a feature set and then the content of a question item is transformed into a numeric form called a feature vector. Because of the poor scalability of neural networks on high-dimension input spaces, several feature reduction methods were investigated to reduce the dimensionality of the feature space. The experimental results indicate that the proposed model can enhance the convergence speed. The results also illustrate that document frequency is the most effective feature reduction method because it maintains the classification precision while enhancing the convergence speed.