Assessing Metacognitive Skills Using Adaptive Neural Networks

Justin Anderson
Kouider Mokhtari, The University of Texas at Tyler
Arun D. Kulkarni, University of Texas at Tyler


The assessment of student's levels of metacognitive knowledge and skills is critical in determining their ability to effectively perform complex cognitive tasks such as solving mathematics or reading comprehension problems. In this paper, we use an adaptive multiplayer perceptron model to categorize participants based on their metacognitive awareness and perceived use of reading strategies while reading. Eight hundred and sixty-five middle school students participated in the study. All participants completed a 30-item instrument- the Metacognitive Awareness-of-Reading Strategies Inventory (MARSI). We used adaptive multi-layer perceptron models to classify participants into three groups based on their metacognitive strategy awareness levels using thirteen and nine attributes representing problem-solving and support reading strategies. The architecture for the neural network models is based on the input data. The number of units in the input layer is equal to the number of attributes and the number of units in the output layer is equal to the number of categories. We classified participants into three categories based on the level of awareness. The models are evaluated using the measures such as user's efficiency and Kappa coefficient that are obtained from the error matrix. We obtained an overall efficiency of 86.92 and 81.89 percent with 13 and 9 input features, respectively. The results indicate that once the network is trained, it can be used to assess student's metacognitive awareness and use of reading strategies with the help of observed attributes.