Abstract:
Plagiarism detection has gained increasing scholarly attention due to the rapid
expansion of digital content and the widespread availability of online academic
resources. Despite the growing body of literature, a comprehensive and up-to-date
bibliometric overview that maps the intellectual structure and research evolution
of plagiarism detection remains limited. To address this gap, this study conducts
a global bibliometric analysis of plagiarism detection research published
between 1990 and 2024. The objectives of the study were (1) to perform a descriptive
analysis of the field of plagiarism detection, and (2) to identify areas
of study that necessitate further investigation in order to advance plagiarism detection.
Bibliometric analysis was performed following the Preferred Reporting
Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines to analyze
the data. The study considered 305 articles from 182 journals in the Scopus
database, which demonstrate the topic’s dynamic growth over the selected period.
The study utilized Biblioshiny and VOSviewer to visualize data. The study identifies
the most relevant sources, the distribution of publications across countries
(both single-country and multi-country publications), and the most distinguished
scholars whose contributions have been the most fruitful over time. Worldwide
scholarly interest has focused on different types of technologies such as machine
learning, deep learning, natural language processing, and text processing to detect
plagiarism. Additionally, the study identified four clusters representing plagiarism
detection techniques related to artificial intelligence, text processing techniques,
plagiarism types, and underlying computer programming theories. Furthermore,
additional research is necessary in the areas of computational linguistics, feature
extraction, text processing, classification of information, semantics, syntactic
analysis, and source code plagiarism detection. Overall, the insights derived from
this bibliometric analysis provide a structured research agenda that supports the
development of more effective, scalable, and theoretically grounded plagiarism detection
methodologies.
