首页|Research from University of Management and Technology Yields New Data on Artific ial Intelligence (Unveiling AI-Generated Financial Text: A Computational Approac h Using Natural Language Processing and Generative Artificial Intelligence)
Research from University of Management and Technology Yields New Data on Artific ial Intelligence (Unveiling AI-Generated Financial Text: A Computational Approac h Using Natural Language Processing and Generative Artificial Intelligence)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – Researchers detail new data in artific ial intelligence. According to news reporting originating from Lahore, Pakistan, by NewsRx correspondents, research stated, “This study is an in-depth explorati on of the nascent field of Natural Language Processing (NLP) and generative Arti ficial Intelligence (AI), and it concentrates on the vital task of distinguishin g between human-generated text and content that has been produced by AI models.” The news reporters obtained a quote from the research from University of Managem ent and Technology: “Particularly, this research pioneers the identification of financial text derived from AI models such as ChatGPT and paraphrasing tools lik e QuillBot. While our primary focus is on financial content, we have also pinpoi nted texts generated by paragraph rewriting tools and utilized ChatGPT for vario us contexts this multiclass identification was missing in previous studies. In t his paper, we use a comprehensive feature extraction methodology that combines T F-IDF with Word2Vec, along with individual feature extraction methods. Important ly, combining a Random Forest model with Word2Vec results in impressive outcomes . Moreover, this study investigates the significance of the window size paramete rs in the Word2Vec approach, revealing that a window size of one produces outsta nding scores across various metrics, including accuracy, precision, recall and t he F1 measure, all reaching a notable value of 0.74. In addition to this, our de veloped model performs well in classification, attaining AUC values of 0.94 for the ‘GPT’ class; 0.77 for the ‘Quil’ class; and 0.89 for the ‘Real’ class.”
University of Management and TechnologyLahorePakistanAsiaArtificial IntelligenceEmerging TechnologiesMachine LearningNatural Language Processing
NETL
NSTL
