Document Cohesion Flow: Striving towards Coherence

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

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

142 Downloads (Pure)


Text cohesion is an important element of discourse
processing. This paper presents a new approach to modeling,
quantifying, and visualizing text cohesion using automated
cohesion flow indices that capture semantic links among
paragraphs. Cohesion flow is calculated by applying
Cohesion Network Analysis, a combination of semantic
distances, Latent Semantic Analysis, and Latent Dirichlet
Allocation, as well as Social Network Analysis. Experiments
performed on 315 timed essays indicated that cohesion flow
indices are significantly correlated with human ratings of text
coherence and essay quality. Visualizations of the global
cohesion indices are also included to support a more facile
understanding of how cohesion flow impacts coherence in
terms of semantic dependencies between paragraphs.
Original languageEnglish
Title of host publicationCogSci 2016 Proceedings
EditorsA. Papafragou, D. Grodner, D. Mirman, J.C. Trueswell
Place of PublicationAustin, TX
PublisherCognitive Science Society
ISBN (Print)978-0-9911967-3-9
Publication statusPublished - Aug 2016
Externally publishedYes
Event38th Annual Conference of the Cognitive Science Society: Recognizing and Representing Events - Philadelphia, United States
Duration: 10 Aug 201613 Aug 2016


Conference38th Annual Conference of the Cognitive Science Society
Abbreviated titleCOGSCI2016
Country/TerritoryUnited States
Internet address


  • Cohesion Flow
  • Natural Language Processing
  • Computational Models
  • Cohesion Network Analysis
  • Coherence
  • Writing Quality


Dive into the research topics of 'Document Cohesion Flow: Striving towards Coherence'. Together they form a unique fingerprint.

Cite this