0% found this document useful (0 votes)
5 views2 pages

Human vs AI Text Classification System

Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
0% found this document useful (0 votes)
5 views2 pages

Human vs AI Text Classification System

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

DEPARTMENT OF COMPUTER SCIENCE AND ENGINEERING

II B. Tech II Sem Mini-Project 1, 2024-2025, GN-22

Specialization in AI

G. Narayanamma Institute of Technology & Science (Autonomous) (For Women)

Approved by AICTE, New Delhi & Affiliated to JNTUH, Hyderabad

Accredited by NBA & NAAC, an ISO 9001:2015 Certified Institution

Shaikpet, Hyderabad-500104

on "Human vs AI Text Classification System"


Under the guidance of Mrs. Nanda Devi. D.R, Assistant Professor

Dept R&D: Yes

Company Name / GNITS: GNITS

23251A0548 Manisha Kancharla manishakancharla61@[Link] 8520975010

23251A0564 Zainah Nazneen zainahnaazneen7@[Link] 7416031931

23251A0524 Rishitha Nomula rishithar35@[Link] 9885853711

Internal Guide Class Coordinator Project Coordinator Head of Department

Abstract
The swift evolution of generative AI is increasingly blurring the boundaries between
machine-produced and human-created text, raising key questions of authenticity in
academics, journalism, and online dialogue. This minor project addresses these challenges
by developing a classification system based on artificial intelligence and natural language
processing. By examining linguistic cues—such as structure of paragraphs, diversity of
sentences, and nuanced stylistic details—the system aims to reliably distinguish between
human and AI-authored content.

Using a carefully compiled dataset with both AI-generated and human-written samples, the
project incorporates robust text processing and interpretable assessment methods,
ensuring meaningful and trustworthy outputs. Performance is evaluated using
internationally accepted metrics to guarantee transparency and credibility.

The resulting Python-based solution and its comprehensive evaluation reports will support
academic ethics and broader communication integrity. Through its focus on interpretability
and clarity, this system sets itself apart from traditional, opaque approaches to content
detection.
Hardware & Software Requirements
Hardware: A laptop with a minimum Intel i5 processor, 8GB RAM, and 256GB SSD storage.

Software: Python 3.7+, NumPy, Pandas, Matplotlib, Seaborn, Flask API for interface, and
standard NLP libraries.

You might also like