AI Text vs. Human Writing: A Machine Learning-Based Detection Approach
Fuente:
Zenodo
Enregistré dans:
| Auteur principal: | |
|---|---|
| Format: | Recurso digital |
| Langue: | anglais |
| Publié: |
Zenodo
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866901463210393600 |
|---|---|
| author | D Vasantha |
| author_facet | D Vasantha |
| contents | <p><span lang="EN-US">With the rapid progress in natural language processing (NLP), artificial intelligence (AI) systems are now capable of <span> </span>generating text that closely matches human writing. While this advancement has many benefits, it also raises concerns related to ethics, trust, and misuse. In this study, we present a detection system that can accurately distinguish between human-written and AI-generated text. Our model uses a combination of classical and deep learning methods, including Random Forest (RF), Logistic Regression (LR), and Long Short-Term Memory (LSTM) networks.. We also analyzed existing work in this area to compare different approaches and understand common challenges. The results highlight the effectiveness of LSTM in capturing the structure and flow of natural language, making it more reliable for this task. Additionally, we discuss the broader impact of this technology on sectors like education, media, and cybersecurity, while also considering ethical concerns such as fairness and sustainability</span><span lang="EN-US">. </span></p> |
| format | Recurso digital |
| id | zenodo_https___doi_org_10_5281_zenodo_17603207 |
| institution | Zenodo |
| language | eng |
| publishDate | 2025 |
| publisher | Zenodo |
| record_format | zenodo |
| spellingShingle | AI Text vs. Human Writing: A Machine Learning-Based Detection Approach D Vasantha : AI generated text detection, Natural language processing(NLP) ,supervised learning, random forest, Text Classifiaction <p><span lang="EN-US">With the rapid progress in natural language processing (NLP), artificial intelligence (AI) systems are now capable of <span> </span>generating text that closely matches human writing. While this advancement has many benefits, it also raises concerns related to ethics, trust, and misuse. In this study, we present a detection system that can accurately distinguish between human-written and AI-generated text. Our model uses a combination of classical and deep learning methods, including Random Forest (RF), Logistic Regression (LR), and Long Short-Term Memory (LSTM) networks.. We also analyzed existing work in this area to compare different approaches and understand common challenges. The results highlight the effectiveness of LSTM in capturing the structure and flow of natural language, making it more reliable for this task. Additionally, we discuss the broader impact of this technology on sectors like education, media, and cybersecurity, while also considering ethical concerns such as fairness and sustainability</span><span lang="EN-US">. </span></p> |
| title | AI Text vs. Human Writing: A Machine Learning-Based Detection Approach |
| topic | : AI generated text detection, Natural language processing(NLP) ,supervised learning, random forest, Text Classifiaction |
| url | https://doi.org/10.5281/zenodo.17603207 |