This article reports the results of using a three-layer back propagation artificial neural network to predict item difficulty in a reading comprehension test. Three classes of variables were examined: text structure, propositional analysis, and cognitive demand. Results demonstrate that the networks can consistently predict item difficulty. (JL)

This study used the residual gain statistic in reading comprehension research in English as a second language to assess individual differences in improvement accruing from learning and training. The subjects were 34 foreign college students with a variety of native languages. A 35-item cloze test with every eighth word eliminated, but with the…