Analysis of Indian and American poetry using topic modeling and Deep learning

Text classification is a supervised machine learning technique that assigns a set of predefined categories or classes to the given text corpora based on the content of the processed text using Natural language processing techniques. Text classification is widely used in numerus applications such as categorizing
the sentiment of the tweets and reviews, classification of news and web pages into multiple categories and automatic classification of emails in to spam or not spam. Under the text categories poetry is a lit- erary text and it is special when compared with the regular prose text. A very less focus is given to the task of classification of poetry by the research community. In this context, this work aimed to classify
poetry using machine learning and deep learning models and to analyze the performance of the algo-rithms. To perform this task, poetry corpus is categorized into multiple classes using Latent Dirichlet Allocation a topic modeling technique. The classification task is carried using Multinomial Bayesian,
SGD models under machine learning methods and LSTM, Bi-LSTM and CNN models under the deep learn-ing methods. The results are evaluated with parameter accuracy. As a result of this experiment the best classification accuracy is achieved using CNN model with 87% by outperforming other models. This shows that for literary text classification CNN can be considered as a best classifier in comparative with the LSTM and Bi-LSTM models.