Differentiating Chat Generative Pretrained Transformer from Humans: Detecting ChatGPT-Generated Text and Human Text Using Machine Learning

Recently, the identification of human text and ChatGPT-generated has become a hot research topic. The current study presents Tunicate Swarm Algorithm with Long Short-Term Memory Recurrent Neural Network (TSA-LSTMRNN) model to detect both as well text. purpose proposed TSA-LSTMRNN method is investigate model’s decision presence any particular pattern. In addition this, technique focuses on designing Term Frequency–Inverse Document Frequency (TF-IDF), word embedding, count vectorizers for feature extraction process. For detection classification processes, LSTMRNN used. Finally, TSA employed selecting parameters approach, which enables improved performance. simulation performance was investigated benchmark databases, outcome demonstrated advantage system over other recent methods maximum accuracy 93.17% 93.83% human- datasets, respectively.