@inproceedings{nazeem-etal-2024-comprehensive,
title = "Comprehensive Plagiarism Detection in {M}alayalam Texts Through Web and Database Integration",
author = "Nazeem, Meharuniza and
Raj, Parvathy and
R. R, Rajeev and
R, Anitha and
S, Navaneeth",
editor = "Lalitha Devi, Sobha and
Arora, Karunesh",
booktitle = "Proceedings of the 21st International Conference on Natural Language Processing (ICON)",
month = dec,
year = "2024",
address = "AU-KBC Research Centre, Chennai, India",
publisher = "NLP Association of India (NLPAI)",
url = "https://aclanthology.org/2024.icon-1.40/",
pages = "349--356",
abstract = "Plagiarism detection techniques have become essential for recognizing instances of plagiarism, particularly in the domain of academics where scientific papers and documents are of prime importance. We propose an application that offers a comprehensive solution for detecting plagiarism in scholarly articles written in Malayalam, enabling users to submit texts, analyze them for plagiarism, and review the results interactively. With the increasing accessibility of digital content, maintaining originality in academic writing has become more tedious. Our research addresses this challenge by providing a solution tailored to the Malayalam language. The application aids researchers and academic institutions in detecting potential plagiarism by accessing web-based content and algorithmic text analysis. The study significantly contributes to the field of plagiarism detection for low resource language such as malayalam and offers a practical way to preserve the originality of Malayalam scholarly work. The performance of four algorithms SequenceMatcher, N-Grams, Rabin-Karp, and Cosine Similarity is thoroughly evaluated. Cosine Similarity, with a 92.45{\%} detection rate, outperformed the others, significantly surpassing Rabin-Karp(65.3{\%}), N-Grams(58.7{\%}) and SequenceMatcher(51.4{\%}). Using this improved efficiency, a user-friendly web application was developed that integrates web search and database comparison features with the Cosine Similarity algorithm."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nazeem-etal-2024-comprehensive">
<titleInfo>
<title>Comprehensive Plagiarism Detection in Malayalam Texts Through Web and Database Integration</title>
</titleInfo>
<name type="personal">
<namePart type="given">Meharuniza</namePart>
<namePart type="family">Nazeem</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Parvathy</namePart>
<namePart type="family">Raj</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rajeev</namePart>
<namePart type="family">R. R</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anitha</namePart>
<namePart type="family">R</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Navaneeth</namePart>
<namePart type="family">S</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 21st International Conference on Natural Language Processing (ICON)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sobha</namePart>
<namePart type="family">Lalitha Devi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Karunesh</namePart>
<namePart type="family">Arora</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>NLP Association of India (NLPAI)</publisher>
<place>
<placeTerm type="text">AU-KBC Research Centre, Chennai, India</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Plagiarism detection techniques have become essential for recognizing instances of plagiarism, particularly in the domain of academics where scientific papers and documents are of prime importance. We propose an application that offers a comprehensive solution for detecting plagiarism in scholarly articles written in Malayalam, enabling users to submit texts, analyze them for plagiarism, and review the results interactively. With the increasing accessibility of digital content, maintaining originality in academic writing has become more tedious. Our research addresses this challenge by providing a solution tailored to the Malayalam language. The application aids researchers and academic institutions in detecting potential plagiarism by accessing web-based content and algorithmic text analysis. The study significantly contributes to the field of plagiarism detection for low resource language such as malayalam and offers a practical way to preserve the originality of Malayalam scholarly work. The performance of four algorithms SequenceMatcher, N-Grams, Rabin-Karp, and Cosine Similarity is thoroughly evaluated. Cosine Similarity, with a 92.45% detection rate, outperformed the others, significantly surpassing Rabin-Karp(65.3%), N-Grams(58.7%) and SequenceMatcher(51.4%). Using this improved efficiency, a user-friendly web application was developed that integrates web search and database comparison features with the Cosine Similarity algorithm.</abstract>
<identifier type="citekey">nazeem-etal-2024-comprehensive</identifier>
<location>
<url>https://aclanthology.org/2024.icon-1.40/</url>
</location>
<part>
<date>2024-12</date>
<extent unit="page">
<start>349</start>
<end>356</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Comprehensive Plagiarism Detection in Malayalam Texts Through Web and Database Integration
%A Nazeem, Meharuniza
%A Raj, Parvathy
%A R. R, Rajeev
%A R, Anitha
%A S, Navaneeth
%Y Lalitha Devi, Sobha
%Y Arora, Karunesh
%S Proceedings of the 21st International Conference on Natural Language Processing (ICON)
%D 2024
%8 December
%I NLP Association of India (NLPAI)
%C AU-KBC Research Centre, Chennai, India
%F nazeem-etal-2024-comprehensive
%X Plagiarism detection techniques have become essential for recognizing instances of plagiarism, particularly in the domain of academics where scientific papers and documents are of prime importance. We propose an application that offers a comprehensive solution for detecting plagiarism in scholarly articles written in Malayalam, enabling users to submit texts, analyze them for plagiarism, and review the results interactively. With the increasing accessibility of digital content, maintaining originality in academic writing has become more tedious. Our research addresses this challenge by providing a solution tailored to the Malayalam language. The application aids researchers and academic institutions in detecting potential plagiarism by accessing web-based content and algorithmic text analysis. The study significantly contributes to the field of plagiarism detection for low resource language such as malayalam and offers a practical way to preserve the originality of Malayalam scholarly work. The performance of four algorithms SequenceMatcher, N-Grams, Rabin-Karp, and Cosine Similarity is thoroughly evaluated. Cosine Similarity, with a 92.45% detection rate, outperformed the others, significantly surpassing Rabin-Karp(65.3%), N-Grams(58.7%) and SequenceMatcher(51.4%). Using this improved efficiency, a user-friendly web application was developed that integrates web search and database comparison features with the Cosine Similarity algorithm.
%U https://aclanthology.org/2024.icon-1.40/
%P 349-356
Markdown (Informal)
[Comprehensive Plagiarism Detection in Malayalam Texts Through Web and Database Integration](https://aclanthology.org/2024.icon-1.40/) (Nazeem et al., ICON 2024)
ACL