The DOI matches its Crossref record; 46 of the 46 references it cites were found in a registry or an index; none of the 43 sources its claims cite is checked for support yet.
Plagiarism types and detection methods: a systematic survey of algorithms in text analysis
Open accessAbstract
Plagiarism in academic and creative writing continues to be a significant challenge, driven by the exponential growth of digital content. This paper presents a systematic survey of various types of plagiarism and the detection algorithms employed in text analysis. We categorize plagiarism into distinct types, including verbatim, paraphrasing, translation, and idea-based plagiarism, discussing the nuances that make detection complex. This survey critically evaluates existing literature, contrasting traditional methods like string-matching with advanced machine learning, natural language processing, and deep learning approaches. We highlight notable works focusing on cross-language plagiarism detection, source code plagiarism, and intrinsic detection techniques, identifying their contributions and limitations. Additionally, this paper explores emerging challenges such as detecting cross-language plagiarism and AI-generated content. By synthesizing the current landscape and emphasizing recent advancements, we aim to guide future research directions and enhance the robustness of plagiarism detection systems across various domains.
Overview
CoChat Summary
TL;DR
This systematic survey reviews plagiarism types and text-analysis detection algorithms, contrasting traditional string matching with ML, NLP, and deep learning approaches. It synthesizes 41 final papers from 2014–2024 and highlights cross-language, source-code, and AI-generated content as key emerging challenges.
Key findings
- The paper categorizes plagiarism into verbatim, paraphrased, idea-based, translation, code, and AI-generated types, plus obfuscated, cross-language, and multilingual/language-independent forms; detection methods are grouped into six primary approaches: textual similarity, semantic similarity, cross-language, machine learning/deep learning, citation/structural, and code-based.
- The review reports an initial search yield of 104 papers, reduced to 47 after restricting to Q1 journals, and finally to 41 included papers. Publication activity peaked in 2020; disciplinary distribution was computer science 41.4%, engineering 19.2%, social sciences 16.2%, decision sciences 13.1%, mathematics 2.0%, business management 4.0%, and neuroscience 1.0%.
- Prevalence figures cited include up to 58% of university students admitting some form of plagiarism, an estimated 1.5% of published papers involving duplicate or unethical reuse, and code plagiarism accounting for nearly 20% of academic misconduct cases reported by universities.
- Reported detection performance examples include El-Rashidy et al. (2024) Plagdet 89.81%/93.92%, Alzahrani and Aljuaid (2022) ~97% accuracy, Glavaš et al. (2018) R@1 = 89.5% and R@10 = 94%, Bartoszuk and Gagolewski (2021) F1 0.967, Liu et al. (2015) 0% false alarm and 5% omission, and Hayawi et al. (2023) 95.74% accuracy for AI-generated text.
Methods
- Systematic review following the PICOS framework and PRISMA guidelines, using Scopus as the primary database with the query “text AND plagiarism AND detection.”
- Filters applied: year range 2014–2024, subject area computer science, full-length peer-reviewed journal articles, journal source type, and English language only.
- Screening yielded 104 papers, then 47 after Q1 restriction; after abstract review and exclusions for non-textual domains, lack of empirical validation, redundancy, methodological limitations, language mismatch, and inaccessibility, 41 papers were included. Analysis categorizes detection methods and provides quantitative publication/disciplinary trends plus critical assessment of efficiency, accuracy, and scalability.
Limitations
- The paper does not present a dedicated limitations section; it states challenges including scalability and resource intensity of deep learning, linguistic and discursive variability, adaptability to emerging obfuscation techniques, and the need for multilingual benchmarks.
- Evident from the text: the review relies on Scopus only, English-language papers only, Q1 journals only, and the 2014–2024 window, which may limit coverage and generalizability.
- Evident from the text: several summarized studies lack accuracy metrics or report limited benchmarks (e.g., “No accuracy provided” for some entries), and the paper notes performance depends on dataset/feature quality and knowledge-base coverage.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Figures
Verification
Claims the paper makes
0 Valid · 0 Not valid · 25 Not checked · 50 Own results and interpretations
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Stable publication activity between 2015 and 2017, indicating sustained interest in refining plagiarism detection methodologies.”
§ 4 Quantitative analysis of reviewed literature on plagiarism detection > 4.1 Publication trends in reviewed papers (2014–2024)
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Rests on an assumption not shown here.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Pre-2018: emphasis on traditional string-matching, n-gram, and citation-based approaches, widely used in early detection tools.”
§ 4 Quantitative analysis of reviewed literature on plagiarism detection > 4.3 Evolution of detection methodologies in reviewed papers
plainstates an association- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Rests on an assumption not shown here.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Engineering (19.2%) accounts for a significant share, likely due to the development of software tools and algorithmic optimizations.”
§ 4 Quantitative analysis of reviewed literature on plagiarism detection > 4.2 Disciplinary distribution of reviewed research
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Rests on an assumption not shown here.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“A notable peak in 2020, reflecting an increased focus on AI-driven detection techniques and the rising concern over AI-generated plagiarism.”
§ 4 Quantitative analysis of reviewed literature on plagiarism detection > 4.1 Publication trends in reviewed papers (2014–2024)
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Rests on an assumption not shown here.
A result the paper states — it cites no source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“As a result, 41 papers were included in the final dataset for this review, providing a solid foundation for analyzing plagiarism detection techniques.”
§ 3 Paper selection methodology > 3.1 Database selection and search strategy
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Rests on an assumption not shown here.
16 more claims
Create a free account to see all 75 claims and every source verdict.
- Probably not a substantial claim. 34
- It may state two separate claims as one. 26
- Borderline: one of the tests for a substantial claim is unclear. 1
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
Each contradiction between two passages listed here was confirmed by an independent check.
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ 6 Plagiarism detection methods > 6.4 Machine learning and deep learning approaches
“El-Rashidy et al. ( 2022 ) Lexical, syntactic, semantic plagiarism Academic texts SVM, Chi-square feature selection”
§ References
“El-RashidyM. A.MohamedR. G.El-FishawyN. A.ShoumanM. A. (2024). An effective text plagiarism detection system based on feature selection and SVM techniques.”
Citations
Cites
Ethics and scientific publication
Benos, D. J., Fabres, J., Farmer, J., Gutierrez, J. P., Hennessy, K., Kosek, D., Lee, J. H., Olteanu, D., Russell, T., Shaikh, F., et al. (2005) · Advances in Physiology Education · doi:10.1152/advan.00056.2004 · Cited by 209
A deep network model for paraphrase detection in short text messages
Agarwal, B., Ramampiaro, H., Helge Langseth, A., & Ruocco, M. (2018) · Information Processing & Management · doi:10.1016/j.ipm.2018.06.005 · Cited by 124
A systematic study of knowledge graph analysis for cross-language plagiarism detection
Franco-Salvador, M., Rosso, P., & Montes-y-Gómez, M. (2016) · Information Processing & Management · doi:10.1016/j.ipm.2015.12.004 · Cited by 105
Déjà vu—A study of duplicate citations in Medline
Errami, M., Hicks, J. M., Fisher, W. G., Trusty, D., Wren, J. D., Long, T. C., & Garner, H. R. (2007) · Bioinformatics · doi:10.1093/bioinformatics/btm574 · Cited by 99
The imitation game: Detecting human and AI-generated texts in the era of ChatGPT and BARD
Hayawi, K., Shahriar, S., & Mathew, S. S. (2024) · Journal of Information Science · doi:10.1177/01655515241227531 · Cited by 77
Franco-Salvador, M., Gupta, P., Rosso, P., & Banchs, R. E. (2016) · Knowledge-Based Systems · doi:10.1016/j.knosys.2016.08.004 · Cited by 67
An academic Arabic corpus for plagiarism detection: design, construction and experimentation
Al-Thwaib, E., HAMMO, B. H., & Yagi, S. (2020) · International Journal of Educational Technology in Higher Education · doi:10.1186/s41239-019-0174-x · Cited by 66
PDLK: Plagiarism detection using linguistic knowledge
Abdi, A., Idris, N. B., Alguliyev, R. M., & Aliguliyev, R. M. (2015) · Expert Systems with Applications · doi:10.1016/j.eswa.2015.07.048 · Cited by 65
Citation‐based plagiarism detection: Practicability on a large‐scale scientific corpus
Gipp, B., Meuschke, N., & Breitinger, C. (2014) · Journal of the Association for Information Science and Technology · doi:10.1002/asi.23228 · Cited by 60
Detection of idea plagiarism using syntax–Semantic concept extractions with genetic algorithm
Kanjirangat, V., & Gupta, D. (2016) · Expert Systems with Applications · doi:10.1016/j.eswa.2016.12.022 · Cited by 52
Cited by
Automated scoring in the era of artificial intelligence: An empirical study with Turkish essays
Aydın, B., Kışla, T., Elmas, N. T., & Bulut, O. (2025) · System · doi:10.1016/j.system.2025.103784 · Cited by 30
Multi-Class Detection of Humanized AI Text Using Machine Learning and Transformer Models
Sharimbayev, B., Kazin, A., & Kadyrov, S. (2025) · International Conference on Computational Intelligence and Knowledge Economy (ICCIKE) · doi:10.1109/iccike67021.2025.11318272 · Cited by 7
Makhmutova, A., Sharimbayev, B., Amirzhanov, A., & Shalkarbay-uly, A. (2026) · Journal of Advances in Information Technology · doi:10.12720/jait.17.3.438-449 · Cited by 8
Self-citationArtificial Intelligence in Academic Writing and Research: Adoption and Effectiveness
Shimray, S. R., & Subaveerapandiyan, A. (2025) · Open Information Science · doi:10.1515/opis-2025-0026 · Cited by 11
Tleubayeva, A., Biloshchytska, S., Kuchanskyi, O., Andrashko, Y., Boluk, P. S., Lisnevskyi, R., & Mukhatayev, A. (2026) · Data · doi:10.3390/data11060133 · Cited by 1
Metadata
- Authors
- Amirzhanov, A., Turan, C., & Makhmutova, A.
- Affiliations
- Suleyman Demirel University (KZ)
- New Uzbekistan University (UZ)
- Corresponding author
- Turan, Cemil
- Venue
- Frontiers in Computer Science
- Publisher
- Frontiers Media SA
- Published
- 2025-03-17
- Volume
- 7
- ISSN
- 2624-9898 (ISSN-L)
- OpenAlex
- W4408537500
- Cited by
- 31
- References
- 43
- Citations by year
- 2026: 22 · 2025: 9
- FWCI
- 31.90
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- Frontiers in Computer Science (publishedVersion, cc-by)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Topics
- Social Sciences › Education › Academic integrity and plagiarism
- Physical Sciences › Computer Science › Information Systems › Software Engineering Research
- Physical Sciences › Computer Science › Artificial Intelligence › Authorship Attribution and Profiling
- Keywords
- plagiarism detection, string matching, natural language processing, deep learning, source code plagiarism, AI-generated content detection
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
A language model drew the claims from the paper on 2026-10-10, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-10 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.













