Werda, Kristika Meza (2026) IMPLEMENTASI SISTEM DETEKSI PLAGIARISME DOKUMEN MENGGUNAKAN COSINE SIMILARITY BERBASIS GUI DENGAN PYTHON DAN TKINTER. Skripsi (Bachelor) thesis, Universitas Muhammadiyah Bengkulu.
![[img]](http://repository.umb.ac.id/style/images/fileicons/text.png) |
Text (Kristika Meza Werda_2155201147_Fulltext)
Kristika Meza Werda_2155201147_Fulltext.pdf - Submitted Version Restricted to Repository staff only Download (5MB) | Request a copy |
|
Text (Kristika Meza Werda_2155201147_Turnitin)
Kristika Meza Werda_2155201147_Turnitin.pdf Restricted to Repository staff only Download (8MB) | Request a copy |
|
Text (Kristika Meza Werda_2155201147_Abstrak + BAB 1)
Kristika Meza Werda_2155201147_Abstrak + BAB 1.pdf - Submitted Version Download (321kB) |
|
Text (Kristika Meza Werda_2155201147_BAB 2)
Kristika Meza Werda_2155201147_BAB 2.pdf - Submitted Version Download (390kB) |
|
Text (Kristika Meza Werda_2155201147_BAB 3)
Kristika Meza Werda_2155201147_BAB 3.pdf - Submitted Version Restricted to Repository staff only Download (760kB) | Request a copy |
|
Text (Kristika Meza Werda_2155201147_BAB 4)
Kristika Meza Werda_2155201147_BAB 4.pdf - Submitted Version Restricted to Repository staff only Download (853kB) | Request a copy |
|
Text (Kristika Meza Werda_2155201147_BAB 5)
Kristika Meza Werda_2155201147_BAB 5.pdf - Submitted Version Download (195kB) |
|
Text (Kristika Meza Werda_2155201147_Ref + Lamp)
Kristika Meza Werda_2155201147_Ref + Lamp.pdf - Submitted Version Download (204kB) |
Abstract
This study aims to design and implement a desktop-based document plagiarism detection system that can be operated offline using the Cosine Similarity algorithm with TF-IDF (Term Frequency-Inverse Document Frequency) weighting, built using the Python programming language with a Tkinter-based Graphical User Interface (GUI). The system implements a text preprocessing pipeline comprising case folding, cleaning, tokenization, and stopword removal using Python regular expressions, followed by TF-IDF weighting to represent documents as numerical vectors, and then calculates document similarity using the Cosine Similarity formula with a score range of 0 to 1. The resulting scores are categorized into four labels: Not Plagiarism, Low Plagiarism, Moderate Plagiarism, and High Plagiarism. The application is built with a three-tab navigation structure covering the Plagiarism Detection tab, the SUS Testing tab, and the Black Box Testing tab, and is equipped with a report export feature to Microsoft Word and Excel formats. Functional testing using Black Box Testing on 20 test scenarios yielded a success rate of 95% (19 out of 20 test cases PASS). The one FAIL test case was caused by an error in the test data design rather than a program logic error. Usability testing using the System Usability Scale (SUS) involving 10 respondents produced an average score of 80.50, classified as "Good", with 70% of respondents rating the system in the Good to Excellent category. The results demonstrate that the system accurately distinguishes between identical documents (score 1.0000), partially paraphrased documents (score 0.6954), and unrelated documents (score 0.0000), and can be operated fully offline without relying on external machine learning libraries.
| Item Type: | Thesis (Skripsi (Bachelor)) |
|---|---|
| Additional Information: | Pembimbing : Khairullah, S.T., M.Kom |
| Uncontrolled Keywords: | Deteksi Plagiarisme, Cosine Similarity, TF-IDF, GUI, Python, Tkinter, Black Box Testing, System Usability Scale |
| Subjects: | Universitas Muhammadiyah Bengkulu > 02-Fakultas Teknik > 55201-(S1) Teknik Informatika 02-Fakultas Teknik > 55201-(S1) Teknik Informatika |
| Divisions: | 02-Fakultas Teknik > 55201-(S1) Teknik Informatika Subjek Terkait > 02-Fakultas Teknik > 55201-(S1) Teknik Informatika |
| Depositing User: | Mrs Hesti Ayu |
| Date Deposited: | 02 Sep 2026 03:14 |
| Last Modified: | 02 Sep 2026 03:14 |
| URI: | http://repository.umb.ac.id/id/eprint/3815 |
Actions (login required)
 |
View Item |