Towards Detecting Textual Plagiarism Using Machine Learning Methods
Year: 2015
Type: dissertation
Abstract: Textual plagiarism is passing off someone else’s text as your own. The current\nstate of the art in plagiarism detection performs well, but often uses a series of\nmanually determined thresholds of metrics in order to determine whether an author\nis guilty of performing plagiarism or not. These thresholds are optimized for\na single data set and are not optimal for all situations or forms of plagiarism. The\ndetection methodologies also require a professional familiar with the algorithms\nin order to be properly adjusted, due to their complexity. Using a pre-classified\ndata set, machine learning methods allow teachers and censors without knowledge\nof the methodology to use a plagiarism detection tool specifically designed\nfor their needs.\nThis thesis demonstrates that a methodology using machine learning, without\nthe need to set thresholds, can match, and in some cases surpass, the top methodologies\nin the current state of the art. With more work, future methodologies may\npossibly outperform both the best commercial and freely available methodologies.
Source: BIBSYS Brage (BIBSYS (Norway))
Author: Rune Borge Kalleberg
Language: English
Subfield: Education
Field: Social Sciences
Domain: Social Sciences
Open Access status: green
OpenAlex ID: W2502605298