@article { author = {Reisi, Ehsan and Mahboob Farimani, Hassan}, title = {Authorship Attribution In Historical And Literary Texts By A Deep Learning Classifier}, journal = {Journal of Applied Intelligent Systems and Information Sciences}, volume = {1}, number = {2}, pages = {118-127}, year = {2020}, publisher = {FANAP Research Center}, issn = {2821-1987}, eissn = {2717-039X}, doi = {10.22034/jaisis.2021.269735.1018}, abstract = {One of the important problems that language and literature scholars face is the difficulty of determining the author of the historical and literary texts. Deep learning, the latest available approaches for solving such problems, provides high accuracy results. In this paper, we show how to overcome ownership claims in historical texts by deep learning methods that are designed for text classification. In this regard, we propose a convolution neural network with a four-part architecture and self-attention mechanism to classify texts. In addition, the proposed method increases the accuracy of Author determination up to 2% in comparison with existing methods. Moreover, in our case study, Khān al-Ikhwān, written by Nāsir-i Khusraw, the author determination accuracy was 86%. Although our focus is on Persian historical textbooks through this article, our method can be applied to other languages effectively.}, keywords = {Text Mining,Deep Learning,authorship attribution,Text Classification,Convolutional Neural Networks}, url = {https://journal.research.fanap.com/article_127044.html}, eprint = {https://journal.research.fanap.com/article_127044_bc0c9ce1c7947fe5b9477d6816cd1be4.pdf} }