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 Video

Updated: May 1, 2026

Constructing and Visualizing Models using Mime-based Machine-learning Framework
06:19

Constructing and Visualizing Models using Mime-based Machine-learning Framework

Published on: July 22, 2025

3.1K

Constructing and validating readability models: the method of integrating multilevel linguistic features with machine

Yao-Ting Sung1, Ju-Ling Chen, Ji-Her Cha

  • 1National Taiwan Normal University, Taipei, Taiwan, sungtc@ntnu.edu.tw.

Behavior Research Methods
|April 2, 2014
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

BRDF-Corrected Vicarious Calibration of FORMOSAT-5 RSI Using RadCalNet: Quantitative Assessment and Implications for TOA Reflectance and NIRv.

Sensors (Basel, Switzerland)·2026
Same author

Ultra-Low Power CMOS Logic and Photodetection in WSe<sub>2</sub> Semiconductors by Selective Area Plasma Doping.

ACS applied materials & interfaces·2026
Same author

How continuous is continuous enough? Comparing the reliability of continuous and discrete scales.

Behavior research methods·2026
Same author

Continuous Rating Scale Analytics (CoRSA): A tool for analyzing continuous and discrete data with item response theory.

Behavior research methods·2025
Same author

An interpretable machine learning approach to evaluate 30-day mortality risk in patients with community-onset bacteremia.

Journal of microbiology, immunology, and infection = Wei mian yu gan ran za zhi·2025
Same author

Ability of ChatGPT to Replace Doctors in Patient Education: Cross-Sectional Comparative Analysis of Inflammatory Bowel Disease.

Journal of medical Internet research·2025

This study introduces multilevel linguistic features for improved text readability models. Integrating these features with support vector machines (SVM) enhances classification accuracy for better reading comprehension analysis.

Area of Science:

  • Computational Linguistics
  • Educational Technology
  • Natural Language Processing

Background:

  • Traditional readability formulas often use generalized linear models (GLMs), which have limitations regarding statistical assumptions and outlier handling.
  • Previous applications of multilevel linguistic features in readability models and their validation have been limited.
  • Existing readability models may suffer from low text classification accuracy due to their inherent limitations.

Purpose of the Study:

  • To develop and validate advanced readability models using multilevel linguistic features.
  • To compare the effectiveness of generalized linear models (GLMs) and support vector machines (SVM) in readability assessment.
  • To explore the integration of word, semantic, syntactic, and cohesion level features for enhanced text analysis.

More Related Videos

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

1.3K

Related Experiment Videos

Last Updated: May 1, 2026

Constructing and Visualizing Models using Mime-based Machine-learning Framework
06:19

Constructing and Visualizing Models using Mime-based Machine-learning Framework

Published on: July 22, 2025

3.1K
Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

1.3K

Main Methods:

  • Development of 31 multilevel linguistic features across word, semantic, syntax, and cohesion levels for Chinese texts.
  • Construction and comparison of four readability models: unilevel/multilevel features with GLMs and SVM.
  • Utilizing support vector machine (SVM) for text classification, addressing limitations of traditional GLMs.

Main Results:

  • Readability models integrating multilevel linguistic features and SVM demonstrated superior performance.
  • The multilevel approach provided a more comprehensive representation of text complexity.
  • SVM-based models showed enhanced classification accuracy compared to GLM-based models.

Conclusions:

  • Multilevel linguistic features significantly improve the accuracy and robustness of readability models.
  • Support vector machines (SVM) offer a more effective approach for text classification in readability analysis.
  • This research highlights the importance of a multilevel perspective for understanding text complexity and reading comprehension.