Poet Classification Using ANN and DNN

Authors : Ekin EKİNCİ, Hidayet TAKCI, Sultan ALAGÖZ

Pages : 10-20

View : 14 | Download : 14

Publication Date : 2022-06-30

Article Type : Research Paper

Abstract :Since statistical analysis of poetry is a challenging task in Natural Language Processing insert ignore into journalissuearticles values(NLP);, making inferences about the poets also becomes a very challenging task. In this study, a dataset of Turkish poems which is obtained for 5 different poets is used to compare classification performance of the Artificial Neural Network insert ignore into journalissuearticles values(ANN); and Deep Neural Network insert ignore into journalissuearticles values(DNN); architectures. While Multilayer Perceptron insert ignore into journalissuearticles values(MLP); is selected for ANN architecture, Convolutional Neural Network insert ignore into journalissuearticles values(CNN); is selected as DNN architecture. Two main feature representation approaches are used for the experiments- Term Frequency-Inverse Document Frequency insert ignore into journalissuearticles values(TF-IDF); is used for ANN and word embedding is used for DNN. As a result of the experiments it has been seen that MLP has the highest performance in terms of accuracy, precision, recall and F-score.
Keywords : Poet classification, Classification, Natural Language Processing NLP, Artificial Neural Network ANN, Deep Neural Network