This application note explores how to address a challenging problem faced by many academics and publishing professionals in recent years: ensuring the integrity of academic writing in universities and publishing houses due to advances in Artificial Intelligence (AI). It distinguishes AI- and human-generated English manuscripts using classifier models such as decision tree, random forest, extra trees, and AdaBoost. It utilizes Scikit learn libraries to provide statistics (precision, accuracy, recall, F1, MCC, and Cohen’s kappa scores) and the confusion matrix to guarantee confidence to the user. The accuracy of the model evaluation for classification ranges from 0.97 to 0.99. There is a text data set of approximately 400 AI-generated texts and around 400 human-generated texts used for training and testing (50/50 random split). The AI texts were generated using detailed prompts that describe the text format of abstracts, introductions, discussions, and conclusions of scientific manuscripts in specific subjects. The tutorials for Gotcha GPT are written in Python by using the highly versatile Google Colaboratory platform. They are made freely available via GitHub (https://github.com/andresilvapimentel/Gotcha-GPT).

中文翻译：

---

Gotcha GPT：确保学术写作的完整性


本应用说明探讨了如何解决近年来许多学者和出版专业人士面临的挑战：由于人工智能 （AI） 的进步，确保大学和出版社学术写作的完整性。它使用分类器模型（如决策树、随机森林、额外树和 AdaBoost）来区分 AI 和人工生成的英文手稿。它利用 Scikit 学习库提供统计数据（精度、准确性、召回率、F1、MCC 和 Cohen 的 kappa 分数）和混淆矩阵，以保证用户的信心。分类的模型评估精度范围为 0.97 到 0.99。有一个文本数据集，其中包含大约 400 个 AI 生成的文本和大约 400 个人类生成的文本，用于训练和测试（50/50 随机拆分）。AI 文本是使用详细的提示生成的，这些提示描述了特定主题的科学手稿的摘要、引言、讨论和结论的文本格式。Gotcha GPT 的教程是使用高度通用的 Google Colaboratory 平台用 Python 编写的。它们通过 GitHub （https://github.com/andresilvapimentel/Gotcha-GPT） 免费提供。