Repository logo
Communities & Collections
Research Outputs
Fundings & Projects
People
Statistics
User Manual
Have you forgotten your password?
  1. Home
  2. Faculty of Computer Science and Engineering
  3. Faculty of Computer Science and Engineering: Conference papers
  4. Fifty ways to detect a ghostwriter
Details

Fifty ways to detect a ghostwriter

Date Issued
2011
Author(s)
Abstract
Ghostwriting became students’ most popular way to avoid
writing of boring essays, or the best way to easily earn by
writing on behalf of another student.
This paper presents several markers indicating a presence of
potential ghostwriters. Proposed methodology suggests
various inspection techniques, which do not prove anything
in isolation. Whenever they are jointly implemented, they
successfully cluster the essays, suggesting plausible
absence, potential and almost certain presence of one or few
ghostwriters. After the initial clustering, all the papers go
through subtle linguistic check. In our sample, later
approach discovered some unexpected phrases which
confirmed the presence of the same ghostwriters not only in
the current, but also in the previous generations.
File(s)
Loading...
Thumbnail Image
Name

FIFTY_WAYS_TO_DETECT_A_GHOSTWRITER.pdf

Size

87.89 KB

Format

Adobe PDF

Checksum

(MD5):99cd258ebfe79599b47915caf156d8dd

⠀

Built with DSpace-CRIS software - Extension maintained and optimized by 4Science

  • Accessibility settings
  • Privacy policy
  • End User Agreement
  • Send Feedback
Repository logo COAR Notify