Detect if an academic monograph was made by an Artificial Intelligence system, using Machine Learning

Huamaní Huamaní G.T.; Tocto P.M. · Proceedings of the LACCEI international Multi-conference for Engineering, Education and Technology (2024) · DOI: 10.18687/laccei2024.1.1.1021

Resumen

This research addresses the use of artificial intelligence (AI) in the educational context, specifically in the detection of academic works generated by AI systems in English. Due to the current development of AI, concerns arise about intellectual property and the quality of learning as long as AI systems generate the monographs that students should complete, this project seeks to propose a solution to this problem, for which the steps are detailed. to design and train a recurrent neural network using TensorFlow and the evaluation of the model using classification metrics such as precision, recall and F1-score, the results obtained show that the created model has good performance in the classification of monographic works generated by AI, with high precision, recall and F1-score values. It is concluded that the model is effective in identifying these jobs.

Instituciones: Universidad Nacional de Ingeniería