Diverse Linguistic Features for Assessing Reading Difficulty of Educational Filipino Texts

TL;DR

This paper develops machine learning models using diverse linguistic features to automatically assess the reading difficulty of Filipino educational texts, aiming to improve learning quality and material selection.

Contribution

It introduces a novel set of linguistic features for Filipino readability assessment and demonstrates the effectiveness of Random Forest models with these features.

Findings

Random Forest achieved 62.7% accuracy

Optimal feature combination improved accuracy to 66.1%

Diverse linguistic features enhance Filipino text difficulty prediction

Abstract

In order to ensure quality and effective learning, fluency, and comprehension, the proper identification of the difficulty levels of reading materials should be observed. In this paper, we describe the development of automatic machine learning-based readability assessment models for educational Filipino texts using the most diverse set of linguistic features for the language. Results show that using a Random Forest model obtained a high performance of 62.7% in terms of accuracy, and 66.1% when using the optimal combination of feature sets consisting of traditional and syllable pattern-based predictors.