Computer-Aided Intervention for Reading Comprehension Disabilities

  • Chia-Ling TsaiEmail author
  • Yong-Guei Lin
  • Wen-Yang Lin
  • Marlene Zakierski
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11528)


Our research work focuses on grouping of students based on error patterns in assessment outcomes for effective teaching of reading comprehension in early elementary education. The work can facilitate placement of students with similar reading disabilities in the same intervention group to optimize corrective actions. We collected ELA (English Language Arts) assessment data from two different schools in NY, USA, involving 365 students in total. To protect individual privacy of the participants, no background information that can possibly lead to their identification is collected for the study. To analyze underlying factors affecting reading comprehension without students’ background information and to be able to evaluate the work, we transformed the problem to a K-nearest neighbor matching problem—an assessment should be matched to other assessments performed by the same student in the feature space. The framework allows exploration of various levels of reading skills as the features and a variety of matching mechanisms. In this paper, we present studies on low-level features using the computer-generated measures adopted by literacy experts for gauging the grade-level readability of a piece of writing, and high-level features using human-identified reading comprehension skills required for answering the assessment questions. For both studies, the matching criterion is the distance between two feature vectors. Overall, the low-level feature set performs better than the high-level set, and the difference is most noticeable for K between 15 and 30.


Reading comprehension Intervention program Feature matching 


  1. 1.
    Common Core State Standards Initiative. Accessed 18 Mar 2019
  2. 2.
    Wren, S.: The Cognitive Foundations of Learning to Read: A Framework. Southwest Educational Development Laboratory, Austin (2001)Google Scholar
  3. 3.
    Danubianu, M., Socaciu, T.: Does data mining techniques optimize the personalized therapy of speech disorders? J. Appl. Comput. Sci. Math. 5(3), 15–18 (2009)Google Scholar
  4. 4.
    Danubianu, M., Pentiuc, S.G., Tobolcea, I., Socaciu, T.: Model of a data mining system for personalized therapy of speech disorders. J. Appl. Comput. Sci. Math. 6(3), 28–32 (2009)Google Scholar
  5. 5.
    Klatt, D.H.: Review of the ARPA speech understanding project. J. Acoust. Soc. Am. 62, 1345 (1977)CrossRefGoogle Scholar
  6. 6.
    Storkel, H.L., Hoover, J.R.: An on-line calculator to compute phonotactic probability and neighborhood density based on child corpora of spoken American English. Behav. Res. Methods 42(2), 497–506 (2010)CrossRefGoogle Scholar
  7. 7.
    Fry, E.: A readability formula that saves Time. J. Read. 11, 513–516 (1968)Google Scholar
  8. 8.
    Graves, M.F., Boettcher, J.A., Peacock, J.L.: Word frequency as a predictor of students’ reading vocabularies. J. Read. Behav. 12(2), 117–127 (1980)CrossRefGoogle Scholar
  9. 9.
    Ryder, R.J., Slate, W.H.: The relationship between word frequency and word knowledge. J. Educ. Res. 81(5), 312–317 (1988)CrossRefGoogle Scholar
  10. 10.
    Mota, N.B., et al.: Speech graphs provide a quantitative measure of thought disorder in psychosis. PLoS ONE 7(4), e34928 (2012)CrossRefGoogle Scholar
  11. 11.
    Stanford Log-linear Part-of-Speech Tagger. Accessed 24 Mar 2019

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Chia-Ling Tsai
    • 1
    Email author
  • Yong-Guei Lin
    • 2
    • 3
  • Wen-Yang Lin
    • 2
  • Marlene Zakierski
    • 4
  1. 1.Iona CollegeNew RochelleUSA
  2. 2.Chung Cheng UniversityChiayiTaiwan
  3. 3.National Yunlin University of Science and TechnologyYunlinTaiwan
  4. 4.Sage CollegesAlbanyUSA

Personalised recommendations