Skip to main content

How do the Match Groups work in the new Similarity Report?

In this guide:

The new Match Groups feature categorizes matches in the Similarity Report based on whether Turnitin detected in-text citations and/or quotation marks.

Turnitin uses machine learning technology to recognize in-text citations and quotation marks associated with matched text. Based on these recognized attributes, the Similarity Report can help you easily recognize the matches where the author attempted to include proper attribution versus those where the author appears to have copied text without attribution. 

Match Groups aim to help you distinguish between integrity issues, teachable moments, and properly-included source text. Since there are innumerable ways to include in-text citations and quotation marks, the Similarity Report won’t get it right every time. This article explains how the Match Groups work and how to provide feedback about this feature.

How citation detection works

The technology that powers Match Groups is trained on English content, and this functionality is currently only available for submissions in English. Citation recognition models have been trained on citations in certain formats: APA, MLA, Turabian, and IEEE numbered citations and references. If a citation is included for a match but is not in one of these formats, the report may--but is less likely to--recognize those as citations. Citations may not be recognized if they are placed very far from the matched text.

Where in-text citations are not recognized, matches will be categorized as “Missing Citation” or “Not Cited or Quoted” (depending on whether quotation marks have been detected).

How quotation detection works

Quotation marks are recognized in any of the following formats:

  • "..."
  • ‘...’
  • «...»
  • »...«
  • „…“
  • 『...』
  • 「...」

Quotation marks are not recognized if they are separated from the text by a space (for example, “  this improperly quoted text”). 

Where quotation marks are not recognized, matches will be categorized as “Missing Quotations” or “Not Cited or Quoted” (depending on whether an in-text citation has been detected).

Was this article helpful?
0 out of 0 found this helpful

Articles in this section

Powered by Zendesk