محمدرضا فرنگی

Predicting students’ performance in a course is one of the major aims of educational data mining systems. In the present study, two and three-layer artificial neural networks (ANN) and neuro-fuzzy systems (NFS) were used to predict Iranian EFL learners’ final scores and compare them with scores given by their instructor. Sixty-six students’ scores in an English reading comprehension course comprising of five sub-scores of midterm (out of 40), quiz (out of 60), final (out of 50), class participation (out of 5) and bonus (out of 2) were used for training the systems. Two and three-layer ANNs and an NFS were trained to predict students’ final scores using training data. Researchers compared the students’ final scores given by their instructor and those achieved through the ANNs and NFS. The results showed that the NFS could predict and deliver scores that were closer to the linear sum of students’ scores. Moreover, three-layer ANN had a better performance than the two-layer ANN. According to these results, data mining techniques could deliver an accurate estimate of students' abilities in a particular course.

This study investigated the relationships between Iranian EFL teachers’ conceptions of assessment and their self-efficacy. For this purpose, 154 Iranian EFL teachers were selected through purposeful sampling and completed the 27-item teachers’ conceptions of assessment scale (TCoA) (Brown, 2006), and the 24-item teachers’ self-efficacy scale (Tschannen-Moran & Hoy, 2001). Multiple regression analysis and ANOVA were used to analyze the data. The results showed that teachers considered assessment as a tool to determine how much have their students learned from instruction, assessment results can be used to modify teaching practices and assessment processes may be inaccurate. Moreover, they argued that assessment is an indicator of school performance and, at the same time, assessment results should be treated cautiously. In addition, the results showed that Iranian EFL teachers had a high level of self-efficacy, were good at asking appropriate questions and answering students’ difficult questions, can assess students’ learning, and provide alternative explanations and examples when learners are confused. The results of multiple regression analysis showed that school accountability and irrelevance predicted students’ engagement, students’ accountability predicted classroom management and improvement predicted instructional strategies. These results may have some implications for EFL teachers' professional development.