Modeling Comprehension Processes via Automated Analyses of Dialogism

Mihai Dascalu, Laura Allen, Danielle S. McNamara, Stefan Trausan-Matu, Scott Crossly

Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingAcademicpeer-review

Abstract

Dialogism provides the grounds for building a comprehensive model of discourse and it is focused on the multiplicity of perspectives (i.e., voices). Dialogism can be present in any type of text, while voices become themes or recurrent topics emerging from the discourse. In this study, we examine the extent that differences between self-explanations and thinkalouds can be detected using computational textual indices derived from dialogism. Students (n = 68) read a text about natural selection and were instructed to generate selfexplanations or think-alouds. The linguistic features of these text responses were analyzed using ReaderBench, an automated text analysis tool. A discriminant function analysis using these features correctly classified 80.9% of the students’ assigned experimental conditions (self-explanation vs. think aloud). Our results indicate that self-explanation promotes text processing that focuses on connected ideas, rather than separate voices or points of view covering multiple topics.
Original languageEnglish
Title of host publicationProceedings of the 39th Annual Meetng of the Cognitive Science Society
Subtitle of host publicationComputatonal Foundatons of Cogniton
PublisherCognitive Science Society
Pages1884-1889
ISBN (Print)978-0-9911967-6-0
Publication statusPublished - 2 Aug 2017
Externally publishedYes
Event39th Annual Meeting of the Cognitive Science Society: Computational Foundations of Cognition - London, United Kingdom
Duration: 26 Jul 201729 Jul 2017
https://mindmodeling.org/cogsci2017/

Conference

Conference39th Annual Meeting of the Cognitive Science Society
Abbreviated titleCogSci2017
CountryUnited Kingdom
CityLondon
Period26/07/1729/07/17
Internet address

Fingerprint

comprehension
text processing
text analysis
discourse
student
linguistics

Keywords

  • COMPREHENSION
  • discourse analysis
  • dialogism
  • Polyphonic model
  • self-explanation
  • think-aloud

Cite this

Dascalu, M., Allen, L., McNamara, D. S., Trausan-Matu, S., & Crossly, S. (2017). Modeling Comprehension Processes via Automated Analyses of Dialogism. In Proceedings of the 39th Annual Meetng of the Cognitive Science Society : Computatonal Foundatons of Cogniton (pp. 1884-1889). Cognitive Science Society.
Dascalu, Mihai ; Allen, Laura ; McNamara, Danielle S. ; Trausan-Matu, Stefan ; Crossly, Scott. / Modeling Comprehension Processes via Automated Analyses of Dialogism. Proceedings of the 39th Annual Meetng of the Cognitive Science Society : Computatonal Foundatons of Cogniton . Cognitive Science Society, 2017. pp. 1884-1889
@inproceedings{84fcaf9ae9044b83849235b3b5717c97,
title = "Modeling Comprehension Processes via Automated Analyses of Dialogism",
abstract = "Dialogism provides the grounds for building a comprehensive model of discourse and it is focused on the multiplicity of perspectives (i.e., voices). Dialogism can be present in any type of text, while voices become themes or recurrent topics emerging from the discourse. In this study, we examine the extent that differences between self-explanations and thinkalouds can be detected using computational textual indices derived from dialogism. Students (n = 68) read a text about natural selection and were instructed to generate selfexplanations or think-alouds. The linguistic features of these text responses were analyzed using ReaderBench, an automated text analysis tool. A discriminant function analysis using these features correctly classified 80.9{\%} of the students’ assigned experimental conditions (self-explanation vs. think aloud). Our results indicate that self-explanation promotes text processing that focuses on connected ideas, rather than separate voices or points of view covering multiple topics.",
keywords = "COMPREHENSION, discourse analysis, dialogism, Polyphonic model, self-explanation, think-aloud",
author = "Mihai Dascalu and Laura Allen and McNamara, {Danielle S.} and Stefan Trausan-Matu and Scott Crossly",
year = "2017",
month = "8",
day = "2",
language = "English",
isbn = "978-0-9911967-6-0",
pages = "1884--1889",
booktitle = "Proceedings of the 39th Annual Meetng of the Cognitive Science Society",
publisher = "Cognitive Science Society",
address = "United States",

}

Dascalu, M, Allen, L, McNamara, DS, Trausan-Matu, S & Crossly, S 2017, Modeling Comprehension Processes via Automated Analyses of Dialogism. in Proceedings of the 39th Annual Meetng of the Cognitive Science Society : Computatonal Foundatons of Cogniton . Cognitive Science Society, pp. 1884-1889, 39th Annual Meeting of the Cognitive Science Society, London, United Kingdom, 26/07/17.

Modeling Comprehension Processes via Automated Analyses of Dialogism. / Dascalu, Mihai; Allen, Laura; McNamara, Danielle S.; Trausan-Matu, Stefan; Crossly, Scott.

Proceedings of the 39th Annual Meetng of the Cognitive Science Society : Computatonal Foundatons of Cogniton . Cognitive Science Society, 2017. p. 1884-1889.

Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingAcademicpeer-review

TY - GEN

T1 - Modeling Comprehension Processes via Automated Analyses of Dialogism

AU - Dascalu, Mihai

AU - Allen, Laura

AU - McNamara, Danielle S.

AU - Trausan-Matu, Stefan

AU - Crossly, Scott

PY - 2017/8/2

Y1 - 2017/8/2

N2 - Dialogism provides the grounds for building a comprehensive model of discourse and it is focused on the multiplicity of perspectives (i.e., voices). Dialogism can be present in any type of text, while voices become themes or recurrent topics emerging from the discourse. In this study, we examine the extent that differences between self-explanations and thinkalouds can be detected using computational textual indices derived from dialogism. Students (n = 68) read a text about natural selection and were instructed to generate selfexplanations or think-alouds. The linguistic features of these text responses were analyzed using ReaderBench, an automated text analysis tool. A discriminant function analysis using these features correctly classified 80.9% of the students’ assigned experimental conditions (self-explanation vs. think aloud). Our results indicate that self-explanation promotes text processing that focuses on connected ideas, rather than separate voices or points of view covering multiple topics.

AB - Dialogism provides the grounds for building a comprehensive model of discourse and it is focused on the multiplicity of perspectives (i.e., voices). Dialogism can be present in any type of text, while voices become themes or recurrent topics emerging from the discourse. In this study, we examine the extent that differences between self-explanations and thinkalouds can be detected using computational textual indices derived from dialogism. Students (n = 68) read a text about natural selection and were instructed to generate selfexplanations or think-alouds. The linguistic features of these text responses were analyzed using ReaderBench, an automated text analysis tool. A discriminant function analysis using these features correctly classified 80.9% of the students’ assigned experimental conditions (self-explanation vs. think aloud). Our results indicate that self-explanation promotes text processing that focuses on connected ideas, rather than separate voices or points of view covering multiple topics.

KW - COMPREHENSION

KW - discourse analysis

KW - dialogism

KW - Polyphonic model

KW - self-explanation

KW - think-aloud

M3 - Conference article in proceeding

SN - 978-0-9911967-6-0

SP - 1884

EP - 1889

BT - Proceedings of the 39th Annual Meetng of the Cognitive Science Society

PB - Cognitive Science Society

ER -

Dascalu M, Allen L, McNamara DS, Trausan-Matu S, Crossly S. Modeling Comprehension Processes via Automated Analyses of Dialogism. In Proceedings of the 39th Annual Meetng of the Cognitive Science Society : Computatonal Foundatons of Cogniton . Cognitive Science Society. 2017. p. 1884-1889