Visualizing topic flow in students' essays

Stephen T. O'Rourke, Rafael A. Calvo, Danielle McNamara

Research output: Contribution to journalArticle

11 Citations (Scopus)

Abstract

Visualizing how the parts of a document relate to each other and producing automatically generated quality measures that people can understand are means that writers can use to improve the quality of their compositions. This paper presents a novel document visualization technique and a measure of quality based on the average semantic distance between parts of a document. We show how the visualization helps tutors mark essays more efficiently and reliably, and how a distance index calculated for the visualizations correlates with grades. The technique is further evaluated using three dimensionality reduction techniques. The results provide evidence that the degree of topic flow between consecutive sentences and paragraphs is related to essay quality.

Original languageEnglish (US)
Pages (from-to)4-15
Number of pages12
JournalEducational Technology and Society
Volume14
Issue number3
StatePublished - 2011
Externally publishedYes

Fingerprint

Visualization
Students
visualization
student
Semantics
tutor
writer
semantics
Chemical analysis
evidence

Keywords

  • Argument flow
  • Document visualizations
  • Writing

ASJC Scopus subject areas

  • Education
  • Sociology and Political Science
  • Engineering(all)

Cite this

Visualizing topic flow in students' essays. / O'Rourke, Stephen T.; Calvo, Rafael A.; McNamara, Danielle.

In: Educational Technology and Society, Vol. 14, No. 3, 2011, p. 4-15.

Research output: Contribution to journalArticle

O'Rourke, ST, Calvo, RA & McNamara, D 2011, 'Visualizing topic flow in students' essays', Educational Technology and Society, vol. 14, no. 3, pp. 4-15.
O'Rourke, Stephen T. ; Calvo, Rafael A. ; McNamara, Danielle. / Visualizing topic flow in students' essays. In: Educational Technology and Society. 2011 ; Vol. 14, No. 3. pp. 4-15.
@article{2fa2d286ad6d4e46991009ba3bd0d0c2,
title = "Visualizing topic flow in students' essays",
abstract = "Visualizing how the parts of a document relate to each other and producing automatically generated quality measures that people can understand are means that writers can use to improve the quality of their compositions. This paper presents a novel document visualization technique and a measure of quality based on the average semantic distance between parts of a document. We show how the visualization helps tutors mark essays more efficiently and reliably, and how a distance index calculated for the visualizations correlates with grades. The technique is further evaluated using three dimensionality reduction techniques. The results provide evidence that the degree of topic flow between consecutive sentences and paragraphs is related to essay quality.",
keywords = "Argument flow, Document visualizations, Writing",
author = "O'Rourke, {Stephen T.} and Calvo, {Rafael A.} and Danielle McNamara",
year = "2011",
language = "English (US)",
volume = "14",
pages = "4--15",
journal = "Educational Technology and Society",
issn = "1436-4522",
publisher = "IEEE Computer Society",
number = "3",

}

TY - JOUR

T1 - Visualizing topic flow in students' essays

AU - O'Rourke, Stephen T.

AU - Calvo, Rafael A.

AU - McNamara, Danielle

PY - 2011

Y1 - 2011

N2 - Visualizing how the parts of a document relate to each other and producing automatically generated quality measures that people can understand are means that writers can use to improve the quality of their compositions. This paper presents a novel document visualization technique and a measure of quality based on the average semantic distance between parts of a document. We show how the visualization helps tutors mark essays more efficiently and reliably, and how a distance index calculated for the visualizations correlates with grades. The technique is further evaluated using three dimensionality reduction techniques. The results provide evidence that the degree of topic flow between consecutive sentences and paragraphs is related to essay quality.

AB - Visualizing how the parts of a document relate to each other and producing automatically generated quality measures that people can understand are means that writers can use to improve the quality of their compositions. This paper presents a novel document visualization technique and a measure of quality based on the average semantic distance between parts of a document. We show how the visualization helps tutors mark essays more efficiently and reliably, and how a distance index calculated for the visualizations correlates with grades. The technique is further evaluated using three dimensionality reduction techniques. The results provide evidence that the degree of topic flow between consecutive sentences and paragraphs is related to essay quality.

KW - Argument flow

KW - Document visualizations

KW - Writing

UR - http://www.scopus.com/inward/record.url?scp=80053559517&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=80053559517&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:80053559517

VL - 14

SP - 4

EP - 15

JO - Educational Technology and Society

JF - Educational Technology and Society

SN - 1436-4522

IS - 3

ER -