Scopus Indexed Publications

Paper Details


Title
Predicting the Appropriate Category of Bangla and English Books for Online Book Store Using Deep Learning
Author
Md. Majedul Islam, Md. Sanzidul Islam, Sharun Akter Khushbu,
Email
majedul15-6784@diu.edu.bd
Abstract

At the era of this technology, we are seeking every stuff online first. Book was the best friend to us, still, it is. But this changed the way and medium by which we are being engaged with the book. Nowadays bookselling is more popular online than physically from the store. So books categorizing correctly is a very important problem. But there are many category books available like—Novel, Fiction, non-Fiction, etc. So manually categorizing books was a big deal for everyone. For that having an automatic book category system that uses a book title to categorizing books will help many people. Here, a method is proposed where Long short-term memory (LSTM) technique is used for categorizing books using books title. This model was trained on 1500 English and Bangla books title of four categories. The model reported promising results with training accuracy was 95.08% for English and 83.81% for Bangla. Different preprocessing techniques such as removing numeric data, null value removal, repeat data remove are used. In the Long short-term memory (LSTM) networks activation function ReLU is used in the hidden layer and softmax for the output layer.

Keywords
Books categorizing Long short-term memory (LSTM) Deep learning
Journal or Conference Name
Soft Computing Techniques and Applications. Advances in Intelligent Systems and Computing
Publication Year
2021
Indexing
scopus