Predicting Text Comprehension, Processing, and Familiarity in Adult Readers

New Approaches to Readability Formulas

Scott A. Crossley, Stephen Skalicky, Mihai Dascalu, Danielle McNamara, Kristopher Kyle

Research output: Contribution to journalArticle

19 Citations (Scopus)

Abstract

Research has identified a number of linguistic features that influence the reading comprehension of young readers; yet, less is known about whether and how these findings extend to adult readers. This study examines text comprehension, processing, and familiarity judgment provided by adult readers using a number of different approaches (i.e., natural language processing, crowd-sourced ratings, and machine learning). The primary focus is on the identification of the linguistic features that predict adult text readability judgments, and how these features perform when compared to traditional text readability formulas such as the Flesch-Kincaid grade level formula. The results indicate the traditional readability formulas are less predictive than models of text comprehension, processing, and familiarity derived from advanced natural language processing tools.

Original languageEnglish (US)
Pages (from-to)1-20
Number of pages20
JournalDiscourse Processes
DOIs
StateAccepted/In press - Mar 19 2017

Fingerprint

Text processing
Linguistics
comprehension
Processing
Learning systems
linguistics
predictive model
language
school grade
rating
Text Comprehension
Reader
Familiarity
Readability
learning
Natural Language Processing
Linguistic Features

ASJC Scopus subject areas

  • Language and Linguistics
  • Communication
  • Linguistics and Language

Cite this

Predicting Text Comprehension, Processing, and Familiarity in Adult Readers : New Approaches to Readability Formulas. / Crossley, Scott A.; Skalicky, Stephen; Dascalu, Mihai; McNamara, Danielle; Kyle, Kristopher.

In: Discourse Processes, 19.03.2017, p. 1-20.

Research output: Contribution to journalArticle

@article{48e827c8cd9644f6bafc3fa1d816714e,
title = "Predicting Text Comprehension, Processing, and Familiarity in Adult Readers: New Approaches to Readability Formulas",
abstract = "Research has identified a number of linguistic features that influence the reading comprehension of young readers; yet, less is known about whether and how these findings extend to adult readers. This study examines text comprehension, processing, and familiarity judgment provided by adult readers using a number of different approaches (i.e., natural language processing, crowd-sourced ratings, and machine learning). The primary focus is on the identification of the linguistic features that predict adult text readability judgments, and how these features perform when compared to traditional text readability formulas such as the Flesch-Kincaid grade level formula. The results indicate the traditional readability formulas are less predictive than models of text comprehension, processing, and familiarity derived from advanced natural language processing tools.",
author = "Crossley, {Scott A.} and Stephen Skalicky and Mihai Dascalu and Danielle McNamara and Kristopher Kyle",
year = "2017",
month = "3",
day = "19",
doi = "10.1080/0163853X.2017.1296264",
language = "English (US)",
pages = "1--20",
journal = "Discourse Processes",
issn = "0163-853X",
publisher = "Routledge",

}

TY - JOUR

T1 - Predicting Text Comprehension, Processing, and Familiarity in Adult Readers

T2 - New Approaches to Readability Formulas

AU - Crossley, Scott A.

AU - Skalicky, Stephen

AU - Dascalu, Mihai

AU - McNamara, Danielle

AU - Kyle, Kristopher

PY - 2017/3/19

Y1 - 2017/3/19

N2 - Research has identified a number of linguistic features that influence the reading comprehension of young readers; yet, less is known about whether and how these findings extend to adult readers. This study examines text comprehension, processing, and familiarity judgment provided by adult readers using a number of different approaches (i.e., natural language processing, crowd-sourced ratings, and machine learning). The primary focus is on the identification of the linguistic features that predict adult text readability judgments, and how these features perform when compared to traditional text readability formulas such as the Flesch-Kincaid grade level formula. The results indicate the traditional readability formulas are less predictive than models of text comprehension, processing, and familiarity derived from advanced natural language processing tools.

AB - Research has identified a number of linguistic features that influence the reading comprehension of young readers; yet, less is known about whether and how these findings extend to adult readers. This study examines text comprehension, processing, and familiarity judgment provided by adult readers using a number of different approaches (i.e., natural language processing, crowd-sourced ratings, and machine learning). The primary focus is on the identification of the linguistic features that predict adult text readability judgments, and how these features perform when compared to traditional text readability formulas such as the Flesch-Kincaid grade level formula. The results indicate the traditional readability formulas are less predictive than models of text comprehension, processing, and familiarity derived from advanced natural language processing tools.

UR - http://www.scopus.com/inward/record.url?scp=85015611560&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85015611560&partnerID=8YFLogxK

U2 - 10.1080/0163853X.2017.1296264

DO - 10.1080/0163853X.2017.1296264

M3 - Article

SP - 1

EP - 20

JO - Discourse Processes

JF - Discourse Processes

SN - 0163-853X

ER -