Text similarity analysis
Measuring similarities and matches between sections and paragraphs.
Software for detecting text similarity
SimilR
Software capable of uncovering text similarities between text documents, which can be operated both locally and as a cloud service — for the automated identification of suspected plagiarism cases.
More about the product
Uncovering text similarities, plagiarism detection
SimilR is software capable of uncovering text similarities between text documents, and it can be operated both locally and as a cloud service. Its basic task is to index, for comparison purposes, the theses held by higher education institutions and other academic content available to us.
The basis of the comparison is the measurement of similarities and matches between document sections and paragraphs. Our innovative business model also generates revenue for the cooperating content owners (institutions), based on how often their relevant documents are used.
The most important features
Plagiarism detection
Automated text similarity analysis
Machine comparison of documents for the automated identification of suspected plagiarism cases — the software generates a preliminary report on cases above the tolerance threshold, which can be used in evaluation and decision-making processes.
Web interface
Upload and results in one place
The document to be checked for plagiarism can be uploaded on a central web interface, and the same interface is also used to view the results.
Configurable analysis
Individual, shared and web corpora
It allows several institutional and individual users to run analyses at the same time, and to change the analysis and filtering parameters individually — taking into account the genre, form and subject-matter characteristics of the texts.
Data security
Your data stays at home
We process institutional content locally, thus avoiding the copyright problems typical of plagiarism checkers — Hungarian-language documents protected by copyright law are not placed on foreign servers or in the ownership of foreign companies.
What does SimilR offer?
Reliable analysis, domestic data handling
Data protection
Institutional content is processed locally, without copyright risk.
Simple web interface
Upload and viewing of results on a single central interface.
Configurable analysis
Individual filtering settings according to the genre and form of the texts.
Multiple users
Simultaneous analyses for several institutional and individual users.
Individual and shared corpora
Analysis on individual, shared and web corpora alike.
Automated report
Preliminary report on suspected plagiarism cases above the tolerance threshold.
Revenue model
Cooperating content owners can also earn revenue from the use of their documents.
FAQ
Frequently asked questions
What documents does SimilR examine?
Primarily the theses of higher education institutions and other academic text content.
How can the software be operated?
It can be operated both locally and as a cloud service, according to the institution's needs.
Where is the data stored and processed?
We process institutional content locally, so protected documents are not placed on foreign servers.
Can the analysis parameters be customised?
Yes, the analysis and filtering parameters can be set individually to suit the genre, form and subject-matter characteristics of the texts.
Enquiry
Ask for a demo or a quote
Our colleagues will gladly show you how the product works — leave your contact details and we will get in touch. Fields marked with an asterisk are required.