Detecting AI-Generated Text Using Machine Learning and Deep Learning Approaches

Abstract

Recent advances in natural language processing may enable artificial intelligence models to generate writing identical to human written form in the future. This might have profound ethical, legal, and social consequences. This study aims to address this problem by developing an accurate AI detector model that distinguishes between AI-generated and human-written texts. Our approach applies k-fold cross-validation to well-established machine learning and deep learning models, including Logistic Regression, Extra Trees Classifier, CNN, RNN, LSTM, etc. Furthermore, our results demonstrate that CNN outperforms the other models in distinguishing AI-generated from human-generated content. Providing a comprehensive analysis of the current state of AI-generated text identification in our assessment of pertinent studies. Our testing yielded positive findings, showing that our strategy is successful, with CNN emerging as the most probable answer. We analyze the research's societal implications, highlighting the possible advantages for various industries while addressing sustainability issues about morality and the environment. The LSTM and RNN models achieve accuracies of 0.83 each in this study. The Detect-CNN model achieves the highest accuracy in this investigation, achieving an accuracy of 0.85.