FTLM: A Fuzzy TOPSIS Language Modeling Approach for Plagiarism Severity Assessment Article Swipe
YOU?
·
· 2024
· Open Access
·
· DOI: https://doi.org/10.1109/access.2024.3438434
· OA: W4401326146
Detecting plagiarism poses a significant challenge for academic institutions, research centers, \nand content-centric organizations, especially in cases involving subtle paraphrasing and content manipulation \nwhere conventional methods often prove inadequate. Our paper proposes FTLM (Fuzzy TOPSIS Language \nModeling), a novel method for detecting plagiarism within decision science. FTLM integrates language \nmodels with fuzzy sorting techniques to assess plagiarism severity by evaluating the similarity of potential \nsolutions to a reference. The method involves two stages: leveraging language modeling to define criteria and \nalternatives and implementing enhanced fuzzy TOPSIS. Word usage patterns, grammatical structures, and \nsemantic coherence represent fuzzy membership functions. Moreover, pre-trained language models enhance \nsemantic similarity analysis. This approach highlights the benefits of combining fuzzy logic’s tolerance for \nimprecision with the semantic evaluation capabilities of advanced language models, thereby offering a \ncomprehensive and contextually aware method for analyzing plagiarism severity. The experimental results \non the benchmark dataset demonstrate effective features that enhance performance on the user-defined \nseverity ranking order.
