多种AI技术在罗马尼亚语文本作者归属上的比较
人工智能
2023-01-25 v2
摘要
确定文本的作者是项困难任务。此处我们比较多种AI技术,在考虑有限数量的词类(介词、副词和连词)的情况下,对多位作者所写的文学文本进行分类。我们还引入了一个由罗马尼亚语写成的文本组成的新数据集,并在其上运行了这些算法。所比较的方法有人工神经网络、支持向量机、多表达式编程、C5.0决策树和k近邻。数值实验首先表明该问题困难,但某些算法能够在测试集上产生尚可的误差。
引用
@article{arxiv.2211.05180,
title = {A comparison of several AI techniques for authorship attribution on Romanian texts},
author = {Sanda Maria Avram and Mihai Oltean},
journal= {arXiv preprint arXiv:2211.05180},
year = {2023}
}
备注
We initially used the Accuracy evaluation tool to compute the macro-accuracy, obtaining a value of 88.84%. We, thereafter discovered that this value was erroneous and used other methods which gave us the value of 80.94% for the macro-accuracy. In this version of the paper we present the python module solution by using sklearn.metrics's classification_report and balanced_accuracy_score