Türkçe Klinik Okuma Değerlendirmesi için R Tabanlı Nicel Hesaplamalı Metin Analizi Aracı.

Saved in:

Bibliographic Details
Title:	Türkçe Klinik Okuma Değerlendirmesi için R Tabanlı Nicel Hesaplamalı Metin Analizi Aracı.
Alternate Title:	R-Based Quantitative Computational Text Analysis Tool for Clinical Reading Assessment in Turkish.
Authors:	ÖZER, Esmehan^1,2,3,4 esmehann@gmail.com, ACAR-ÜNALGAN, Sema^2,3,4,5, ARTUVANKORKMAZ, Hazal^2,3,4,6, TEMELTÜRK, Rahime Duygu^3,4,7,8,9, AYDIN, Özgür^2,3,8,10
Source:	Pamukkale University Journal of Education / Pamukkale Üniversitesi Eğitim Fakültesi Dergisi. 2026, Issue 66, p329-347. 38p.
Subject Terms:	Reading ability testing, Readability formulas, Linguistic analysis, Text mining, Linguistic complexity, Programming languages, Turkish language
Abstract (English):	This study aims to develop a computational text analysis tool based on R programming environment to evaluate the quantitative linguistic characteristics of texts used in the clinical assessment of reading skills, and to test newly created texts using this tool. In this context, the narrative text "Double Surprise" and the informative text "Starfish" were written by researchers at three different levels of linguistic and structural complexity. Quantitative parameters such as orthographic similarity (OLD-20), bigram frequency, word frequency, morphological complexity, and readabilityin total six tests were calculated using relevant R packages ("tidytext," "vwr," and "strngram" packages). Texts M2a and M2b were determined to be clustered closest texts in terms of linguistic parameters. Thus, quantitative criteria related to the texts to be used in the assessment of reading skills were established and a text analysis tool was developed in the R language for the first time in Turkish, in addition; the produced texts were tested using this developed tool. The study provides a data-driven and reproducible method for quantitative text evaluation and contributes to Turkish reading materials for research and diagnostic applications. [ABSTRACT FROM AUTHOR]
Abstract (Turkish):	Bu çalışma, okuma becerilerinin klinik değerlendirmesinde kullanılan metinlerin nicel dilbilimsel özelliklerini değerlendirmek üzere R programlama dili temelli bilgisayar destekli bir metin analiz aracı geliştirmek ve bu araçla yeni oluşturulan metinleri test etmeyi amaçlamaktadır. Bu bağlamda, araştırmacılar tarafından anlatı metni "Çifte Sürpriz" ve bilgilendirici metin "Deniz Yıldızları", dilbilimsel ve yapısal karmaşıklık açısından üç farklı düzeyde yazılmıştır. Ortografik benzerlik (OLD-20), bigram sıklığı, sözcük sıklığı, morfolojik karmaşıklık ve okunabilirlik gibi nicel parametreler, ilgili R paketleri ("tidytext", "vwr" ve "strngram" paketleri) kullanılarak toplam altı testte hesaplanmıştır. M2a ve M2b metinlerinin, dilbilimsel parametreler açısından birbirine en yakın metinler olduğu belirlenmiştir. Böylelikle, okuma becerilerinin değerlendirilmesinde kullanılacak metinlere ilişkin nicel kriterler belirlenmiş ve Türkçede ilk kez R dilinde bir metin analiz aracı geliştirilmiş; ayrıca, üretilen metinler bu geliştirilen araç kullanılarak test edilmiştir. Çalışma, nicel metin değerlendirmesi için veriye dayalı ve tekrarlanabilir bir yöntem sunarak araştırma ve tanılama uygulamaları için Türkçe okuma materyallerine katkı sağlamaktadır. [ABSTRACT FROM AUTHOR]
	Copyright of Pamukkale University Journal of Education / Pamukkale Üniversitesi Eğitim Fakültesi Dergisi is the property of Pamukkale University Journal of Education and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database:	Education Research Complete

Description
Abstract:	This study aims to develop a computational text analysis tool based on R programming environment to evaluate the quantitative linguistic characteristics of texts used in the clinical assessment of reading skills, and to test newly created texts using this tool. In this context, the narrative text "Double Surprise" and the informative text "Starfish" were written by researchers at three different levels of linguistic and structural complexity. Quantitative parameters such as orthographic similarity (OLD-20), bigram frequency, word frequency, morphological complexity, and readabilityin total six tests were calculated using relevant R packages ("tidytext," "vwr," and "strngram" packages). Texts M2a and M2b were determined to be clustered closest texts in terms of linguistic parameters. Thus, quantitative criteria related to the texts to be used in the assessment of reading skills were established and a text analysis tool was developed in the R language for the first time in Turkish, in addition; the produced texts were tested using this developed tool. The study provides a data-driven and reproducible method for quantitative text evaluation and contributes to Turkish reading materials for research and diagnostic applications. [ABSTRACT FROM AUTHOR]
ISSN:	13010085
DOI:	10.9779/pauefd.1619827