Comparative Analysis of Cosine Similarity, Jaccard Similarity, and Overlap Similarity for Detecting Cheating Patterns in Online Exams

Authors

  • Musa Faneer Libyan Academy for postgraduate Studies, School of Engineering and Applied Sciences
  • Abdaroof Abdalla Otman Alzintan University, Faculty of information Technology

DOI:

https://doi.org/10.64095/saj.v2i1.900

Keywords:

Online exams, cheating detection, Cosine Similarity, Jaccard Similarity, Overlap Similarity.

Abstract

This study investigates the effectiveness of three similarity algorithms, namely Cosine Similarity, Jaccard Similarity, and Overlap Similarity, for detecting cheating patterns in Moodle-based online examinations. The study addresses the challenge of identifying unauthorized collaboration in e-learning environments by analyzing essay responses from a dataset of 45 students and evaluating the performance of different similarity-based detection approaches. The results show that Cosine Similarity achieved the highest overall performance with an accuracy of 0.75, precision of 0.75, recall of 1.0, and an F1-score of 0.857. Jaccard Similarity ac hieved an accuracy of 0.70, demonstrating better performance in identifying low similarity cases, while Overlap Similarity achieved an accuracy of 0.72, providing a balanced detection capability for moderate similarity levels. These findings highlight the importance of selecting appropriate similarity measures according to data characteristics and contribute to improving automated cheating detection systems in Moodle-based e-learning environments.

References

A. M. Duhaim, S. O. Al-Mamory, and M. Salih, “Cheating detection in online exams during COVID-19 pandemic,” EasyChair Preprint, 2021.

G. Moukhliss, R. F. Hilali, and H. Belhadaoui, “Intelligent solution for automatic online exam monitoring,” International Journal of Electrical and Computer Engineering (IJECE), vol. 13, no. 5, pp. 5333–5341, Oct. 2023, doi: 10.11591/ijece.v13i5.pp5333-5341.

C. Cleophas, C. Hönnige, F. Meisel, and P. Meyer, “Who’s cheating? Mining patterns of collusion from text and events in online exams,” INFORMS Transactions on Education, vol. 23, no. 2, pp. 84–94, 2022, doi: 10.1287/ited.2021.0260.

T. P. Rinjeni, A. Indriawan, and N. A. Rakhmawati, “Matching scientific article titles using Cosine Similarity and Jaccard Similarity algorithm,” Procedia Computer Science, vol. 234, pp. 553–560, 2024, doi: 10.1016/j.procs.2024.03.039.

Z. Liu, J. Zhu, X. Cheng, and Q. Lu, “Optimized algorithm design for text similarity detection based on artificial intelligence and natural language processing,” Procedia Computer Science, vol. 228, pp. 195–202, 2023, doi: 10.1016/j.procs.2023.11.023.

X. Hu et al., “A multi-perspective adaptive cheating detection system for online examinations based on artificial intelligence,” Applied Sciences, vol. 14, no. 10, p. 4048, 2024, doi: 10.3390/app14104048.

M. Shih et al., “Human-in-the-loop AI framework for detecting cheating rings in online assessments,” arXiv preprint arXiv:2403.14711, 2024.

Downloads

Published

30-06-2026

How to Cite

Faneer, M., & Otman, A. . (2026). Comparative Analysis of Cosine Similarity, Jaccard Similarity, and Overlap Similarity for Detecting Cheating Patterns in Online Exams. Sahel Almarifah Journal for Humanities and Applied Sciences, 2(1), 302–318. https://doi.org/10.64095/saj.v2i1.900

Issue

Section

Articles