A Support System for Extensive Reading using English News on the Web

On language learning for English as a second language (ESL) learners, extensive reading is one of methods that can improve reading comprehension ability. Extensive reading is a method to read a lot of sentences that learners can fluently read without a dictionary. In this paper, we focus on English news on the Web as reading materials for extensive reading. By using English news as reading materials, learners can improve their reading comprehension ability, and also gain a better understanding of general education and hot topics all over the world. The purpose of our research is to construct a system that supports extensive reading for Japanese ESL learners using English news on the Web. This paper describes a system configuration and support functions of the proposed system under development. It also explains analysis results of the proposes a method to predict the learners’ vocabulary level using SVM (Support Vector Machine) based on the difficulty level of words and distributed representations of words. The experimental results show that accuracy of prediction can be improved by using distributed representations of words.