Design and Evaluation of Different pq-gram Variants for Grammar-Based Text Analysis

Thesis Type Bachelor
Thesis Status
Finished
Student Philipp Pobitzer
Init
Final
Start
Thesis Supervisor
Contact
Research Field

It has been shown that pq-grams are a successful feature for determining authorships and to detect plagiarism in text documents.

The aim of this thesis is to enhance the original concept of pq-grams by developing different variants. In order to quantify the variants, extensive evaluations should be made.