Computational Text Analysis and Reading Comprehension Exam Complexity : Towards Automatic Text Classification

This book delineates a range of linguistic features that characterise the reading texts used at the B2 (Independent User) and C1 (Proficient User) levels of the Greek State Certificate of English Language Proficiency exams in order to help define text difficulty per level of competence.

In addition, it examines whether specific reader variables influence test takers’ perceptions of reading comprehension difficulty.

The end product is a Text Classification Profile per level of competence and a formula for automatically estimating text difficulty and assigning levels to texts consistently and reliably in accordance with the purposes of the exam and its candidature-specific characteristics.