Intelligent Scoring in an English Reading Comprehension Course Using Artificial Neural Networks and Neuro-fuzzy Systems

  • سال انتشار: 1402
  • محل انتشار: فصلنامه آموزش مهارتهای زبان، دوره: 42، شماره: 4
  • کد COI اختصاصی: JR_JTLS-42-4_001
  • زبان مقاله: انگلیسی
  • تعداد مشاهده: 59
دانلود فایل این مقاله

نویسندگان

Mohamadreza Farangi

Department of Languages and Linguistics, Shiraz University, Shiraz, Iran

Iman Zabbah

Faculty of Computer engineering, Islamic Azad university, Torbati-e-Heydariyeh Branch

چکیده

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 ۴۰), quiz (out of ۶۰), final (out of ۵۰), class participation (out of ۵) and bonus (out of ۲) 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.

کلیدواژه ها

Educational Data Mining, ANN, NFS, Subjective scoring, Intelligent scoring, Reading comprehension

اطلاعات بیشتر در مورد COI

COI مخفف عبارت CIVILICA Object Identifier به معنی شناسه سیویلیکا برای اسناد است. COI کدی است که مطابق محل انتشار، به مقالات کنفرانسها و ژورنالهای داخل کشور به هنگام نمایه سازی بر روی پایگاه استنادی سیویلیکا اختصاص می یابد.

کد COI به مفهوم کد ملی اسناد نمایه شده در سیویلیکا است و کدی یکتا و ثابت است و به همین دلیل همواره قابلیت استناد و پیگیری دارد.