A Prediction Model of Sentence Reading Time Based on Linguistic Features and EFL Learners’ Reading Ability

• Yoshimi Takehiko

  Ryukoku University

• Kotani Katsunori

  Kansai Gaidai University

• Kutsumi Takeshi

  Sharp Corporation

• Sata Ichiko

  Sharp Corporation

• Isahara Hitoshi

  National Institute of Information and Communications Technology

Bibliographic Information

Other Title

• テキストの言語的特徴と英語学習者の英文読解能力に基づく英文読解時間予測モデル
• テキスト言語的特徴と英語学習者の英文読解能力に基づく英文読解時間予測モデル
• テキスト ゲンゴテキ トクチョウ ト エイゴ ガクシュウシャ ノ エイブン ドッカイ ノウリョク ニ モトズク エイブン ドッカイ ジカン ヨソク モデル

Abstract

This paper proposes a model of predicting EFL learners’ sentence reading time based on learners’ reading ability and linguistic features of a sentence. The reading ability here means the learners’ TOEIC (Test of English for International Communications) scores, and the linguistic features indicate lexical, syntactic and discourse complexities. We use natural language processing technology to automatically extract the linguistic features from the sentences, and construct the model by using the Support Vector Machines as a learning mechanism to combine the learners’ and the linguistic features.   An experiment has shown that the proposed model predicts reading time with an error rate of 18.8%, which is lower than the error rates marked by other models.

Journal

• Transactions of Japanese Society for Information and Systems in Education

  Transactions of Japanese Society for Information and Systems in Education 25 (3), 272-281, 2008-11-30

  Japanese Society for Information and Systems in Education

Keywords

• 英語学習
• 英文読解
• 読解時間
• 自然言語処理
• サポートべクターマシン

Details

• CRID: 1390845713076331008
• NII Article ID: 130007629840
• NII Book ID: AN10474042
• DOI: 10.14926/jsise.25.272
• ISSN: 21880980
• ISSN: 13414135
• NDL BIB ID: 9784604
• Web Site: https://ndlsearch.ndl.go.jp/books/R000000004-I9784604
• Text Lang: ja
• Data Source:
  • JaLC
  • NDL
  • CiNii Articles
  • KAKEN
• Abstract License Flag: Disallowed