Unmasking the AI Hand: A Machine Learning Approach to Deciphering Authorship

In an era of explosive data growth, accurate text analysis tools are paramount. The surge of AI-generated texts presents a pressing challenge: discerning human-written content from AI-generated content. This affects text analysis accuracy, necessitating innovative solutions. We introduce an AI-driven model within the Model-View-Controller (MVC) architecture, categorising text as AI-generated or human-authored. Leveraging supervised learning, the model uses Count Vectorizers and Multinomial Naive Bayes algorithm for training and classification. The proposed model shows a good accuracy of 86.2%. This, with enhanced precision and F1 scores, underscores efficacy in classifying text origins. Beyond its immediate contributions, our model promises to reshape content authenticity verification, from AI-generated social media posts to verifying news sources. The model offers future directions, advancing AI-generated content detection. As AI-generated content evolves, our approach ensures credibility and reliability in text analysis within the MVC framework, addressing the critical need to navigate the AI-generated content landscape.