Scribd
Upload
2 views1 page

ieee highlight

The document discusses a machine learning-based framework aimed at identifying AI-generated text in academia, addressing concerns about academic integrity. It combines multiple techniques such as stylometry and semantic analysis, and includes both supervised classification models and unsupervised anomaly detection. The framework also integrates with plagiarism detection tools and emphasizes ethical considerations while adapting to the evolving landscape of AI content.

Uploaded by

vijay12032k
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
2 views1 page

ieee highlight

The document discusses a machine learning-based framework aimed at identifying AI-generated text in academia, addressing concerns about academic integrity. It combines multiple techniques such as stylometry and semantic analysis, and includes both supervised classification models and unsupervised anomaly detection. The framework also integrates with plagiarism detection tools and emphasizes ethical considerations while adapting to the evolving landscape of AI content.

Uploaded by

vijay12032k
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 1

Identifying AI-Written Text in Academia: A Machine

Learning-Based Framework
• Challenge of AI-Generated Text – Addresses the growing concern of AI-written content
affecting academic integrity.

• Machine Learning-Based Framework – Proposes a system that uses ML to detect AI-


generated text.

• Combination of Multiple Techniques – Integrates stylometry, semantic analysis, and


citation pattern recognition.

• Supervised Classification Models – Uses lexical diversity, syntactic complexity, and


redundancy patterns for classification.

• Unsupervised Anomaly Detection – Flags unusual stylistic deviations to identify AI-


generated content.

• Integration with Plagiarism Detection – Works alongside traditional plagiarism tools for
better accuracy.

• Human Expert Review – Involves experts to validate suspicious sections and ensure
correctness.

• Ethical Considerations – Addresses both technical and ethical aspects of AI detection in


academia.

• Adaptability to AI Evolution – Designed to keep up with the rapid advancement of AI-


generated content.

• Preserving Academic Authenticity – Aims to protect the originality of research and


scholarly writing.

You might also like