Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Machine Learning Based Evaluation of Reading and Writing Difficulties.

Mamoru Iwabuchi1, Rumi Hirabayashi1, Kenryu Nakamura1

  • 1RCAST, the University of Tokyo, Tokyo, Japan.

Studies in Health Technology and Informatics
|September 7, 2017
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Machine Learning-Based Classification and Dynamic Analysis of Tear Film Lipid Layer Using Smartphone-Based Interferometry: A Pilot Study.

Eye & contact lensยท2026
See all related articles

Machine learning accurately assesses reading and writing skills in schoolchildren. This automated evaluation method shows improved prediction compared to traditional rule-based decisions for educational assessments.

Area of Science:

  • Educational Psychology
  • Machine Learning Applications
  • Child Development

Background:

  • Early identification of reading and writing difficulties is crucial for academic success.
  • Traditional assessment methods can be time-consuming and subjective.
  • Developing automated tools can improve efficiency and objectivity in skill evaluation.

Purpose of the Study:

  • To investigate the feasibility of using non-parametric machine learning (ML) for automated assessment of reading and writing skills.
  • To compare the predictive accuracy of ML regression against rule-based decision systems for schoolchildren's literacy.
  • To evaluate the URAWSS (Understanding Reading and Writing Skills of Schoolchildren) test data for ML analysis.

Main Methods:

  • Utilized a non-parametric machine learning regression technique.
Keywords:
URAWSSdysgraphiadyslexiaevaluationmachine learning

Related Experiment Videos

  • Applied the method to test data from 168 schoolchildren across grades 1-9.
  • Compared ML predictions with outcomes from ordinary rule-based decision systems.

    • Main Results:

    • Machine learning regression demonstrated superior predictive performance.
    • The ML approach offered a more accurate assessment than conventional rule-based methods.
    • Successful application of ML to the URAWSS dataset.

    Conclusions:

    • Non-parametric ML regression is a viable and effective tool for the automated evaluation of reading and writing difficulties.
    • ML-based assessment holds potential for enhancing the accuracy and efficiency of educational diagnostics.
    • This study supports the integration of ML in educational assessment tools for early intervention and support.