Idea Generation in Student Writing

Computational Assessments and Links to Successful Writing

Scott A. Crossley, Kasia Muldner, Danielle McNamara

Research output: Contribution to journalArticle

7 Citations (Scopus)

Abstract

Idea generation is an important component of most major theories of writing. However, few studies have linked idea generation in writing samples to assessments of writing quality or examined links between linguistic features in a text and idea generation. This study uses human ratings of idea generation, such as idea fluency, idea flexibility, idea originality, and idea elaboration, to analyze the extent to which idea generation relates to human judgments of essay quality in a corpus of college student essays. In conjunction with this analysis, linguistic features extracted from the essays are used to develop a predictive model of idea generation to further understand relations between the language features in an essay and the idea generation scores assigned to that essay. The results indicate that essays rated as containing a greater number of ideas that were flexible, original, and elaborated were judged to be of higher quality. Two of these features (elaboration and originality) were significant predictors of essay quality scores in a regression analysis that explained 33% of the variance in human scores. The results also indicate that idea generation is strongly linked to language features in essays. Specifically, the use of unique multiword units, more difficult words, semantic but not lexical similarities between paragraphs, and fewer word repetitions explained 80% of the variance in human scores of idea generation. These results have implications for writing theories and writing practice.

Original languageEnglish (US)
Pages (from-to)328-354
Number of pages27
JournalWritten Communication
Volume33
Issue number3
DOIs
StatePublished - Jul 1 2016

Fingerprint

Linguistics
Students
Regression analysis
student
Semantics
linguistics
Computational
Student Writing
predictive model
language
regression analysis
flexibility
rating
semantics

Keywords

  • cognitive writing models
  • college student essays
  • corpus linguistics
  • linguistic features and writing quality
  • linguistics
  • natural language processing

ASJC Scopus subject areas

  • Communication
  • Literature and Literary Theory

Cite this

Idea Generation in Student Writing : Computational Assessments and Links to Successful Writing. / Crossley, Scott A.; Muldner, Kasia; McNamara, Danielle.

In: Written Communication, Vol. 33, No. 3, 01.07.2016, p. 328-354.

Research output: Contribution to journalArticle

@article{859bac07b9bb4b0fbd4aa8dc3dafaeee,
title = "Idea Generation in Student Writing: Computational Assessments and Links to Successful Writing",
abstract = "Idea generation is an important component of most major theories of writing. However, few studies have linked idea generation in writing samples to assessments of writing quality or examined links between linguistic features in a text and idea generation. This study uses human ratings of idea generation, such as idea fluency, idea flexibility, idea originality, and idea elaboration, to analyze the extent to which idea generation relates to human judgments of essay quality in a corpus of college student essays. In conjunction with this analysis, linguistic features extracted from the essays are used to develop a predictive model of idea generation to further understand relations between the language features in an essay and the idea generation scores assigned to that essay. The results indicate that essays rated as containing a greater number of ideas that were flexible, original, and elaborated were judged to be of higher quality. Two of these features (elaboration and originality) were significant predictors of essay quality scores in a regression analysis that explained 33{\%} of the variance in human scores. The results also indicate that idea generation is strongly linked to language features in essays. Specifically, the use of unique multiword units, more difficult words, semantic but not lexical similarities between paragraphs, and fewer word repetitions explained 80{\%} of the variance in human scores of idea generation. These results have implications for writing theories and writing practice.",
keywords = "cognitive writing models, college student essays, corpus linguistics, linguistic features and writing quality, linguistics, natural language processing",
author = "Crossley, {Scott A.} and Kasia Muldner and Danielle McNamara",
year = "2016",
month = "7",
day = "1",
doi = "10.1177/0741088316650178",
language = "English (US)",
volume = "33",
pages = "328--354",
journal = "Written Communication",
issn = "0741-0883",
publisher = "SAGE Publications Inc.",
number = "3",

}

TY - JOUR

T1 - Idea Generation in Student Writing

T2 - Computational Assessments and Links to Successful Writing

AU - Crossley, Scott A.

AU - Muldner, Kasia

AU - McNamara, Danielle

PY - 2016/7/1

Y1 - 2016/7/1

N2 - Idea generation is an important component of most major theories of writing. However, few studies have linked idea generation in writing samples to assessments of writing quality or examined links between linguistic features in a text and idea generation. This study uses human ratings of idea generation, such as idea fluency, idea flexibility, idea originality, and idea elaboration, to analyze the extent to which idea generation relates to human judgments of essay quality in a corpus of college student essays. In conjunction with this analysis, linguistic features extracted from the essays are used to develop a predictive model of idea generation to further understand relations between the language features in an essay and the idea generation scores assigned to that essay. The results indicate that essays rated as containing a greater number of ideas that were flexible, original, and elaborated were judged to be of higher quality. Two of these features (elaboration and originality) were significant predictors of essay quality scores in a regression analysis that explained 33% of the variance in human scores. The results also indicate that idea generation is strongly linked to language features in essays. Specifically, the use of unique multiword units, more difficult words, semantic but not lexical similarities between paragraphs, and fewer word repetitions explained 80% of the variance in human scores of idea generation. These results have implications for writing theories and writing practice.

AB - Idea generation is an important component of most major theories of writing. However, few studies have linked idea generation in writing samples to assessments of writing quality or examined links between linguistic features in a text and idea generation. This study uses human ratings of idea generation, such as idea fluency, idea flexibility, idea originality, and idea elaboration, to analyze the extent to which idea generation relates to human judgments of essay quality in a corpus of college student essays. In conjunction with this analysis, linguistic features extracted from the essays are used to develop a predictive model of idea generation to further understand relations between the language features in an essay and the idea generation scores assigned to that essay. The results indicate that essays rated as containing a greater number of ideas that were flexible, original, and elaborated were judged to be of higher quality. Two of these features (elaboration and originality) were significant predictors of essay quality scores in a regression analysis that explained 33% of the variance in human scores. The results also indicate that idea generation is strongly linked to language features in essays. Specifically, the use of unique multiword units, more difficult words, semantic but not lexical similarities between paragraphs, and fewer word repetitions explained 80% of the variance in human scores of idea generation. These results have implications for writing theories and writing practice.

KW - cognitive writing models

KW - college student essays

KW - corpus linguistics

KW - linguistic features and writing quality

KW - linguistics

KW - natural language processing

UR - http://www.scopus.com/inward/record.url?scp=84977543128&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84977543128&partnerID=8YFLogxK

U2 - 10.1177/0741088316650178

DO - 10.1177/0741088316650178

M3 - Article

VL - 33

SP - 328

EP - 354

JO - Written Communication

JF - Written Communication

SN - 0741-0883

IS - 3

ER -