Abstract
The prevalence of academic misconduct, specifically contract cheating, is a rising concern in higher education institutions globally. Among the recent advancements, Generative Artificial Intelligence (genAI) has exacerbated the situation by offering authentically generated writings, making detection through traditional plagiarism tools ineffective. This paper explores the development and application of students' academic writing profiles, using a combination of word embedding (Word2Vec) and stylistic feature extraction techniques. By leveraging a Siamese neural network, our method focuses on recognising distinctive writing styles, a concept rooted in Authorship Verification (AV). Our approach's efficacy evaluates favourably against other AV methods and is tested against AI-generated texts deliberately designed to mimic student writing. The study emphasises the importance of understanding individual academic writing styles to identify outsourcing or AI-generated work effectively.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
