Performance analysis of a novel hybrid deep learning approach in classification of quality-related English text
Myagmarsuren Orosoo, G. Santhakumar, Narmandakh Bayarsaikhan, Yaisna Rajkumari, Gulnaz Fatma, R. Manikandan, B. Kiran Bala
Abstract
Text classification technique is advancing rapidly alongside AI technology, showing signs of maturity. Moreover, there are always many unrestricted constraints that text classification must deal with in practical settings. English text is indeed a significant component of textual data and a significant source of data for persons seeking data from other countries. This study enhances the text classification method currently in use using text classification depending upon English quality. By using an illustration of English quality-related text classification systems, the concept as well as execution of text classification systems is demonstrated, concluding the study on text classification algorithms. The main task of this article is to categorize, and analyze huge volumes of information in English text using technique of integrating qualitative. Therefore, the fundamental components of superior English compositions are attained using Lion Optimization Algorithm (LOA). Convolutional Neural Network-Long Short Term Memory (CNN-LSTM) is utilized to classify the obtained texts. If there is a lot of training input, the typical English text classification method can easily display flaws like ambiguous characteristic elements. In light of such issues, the research suggests a quality-related English text classification approach based on convolutional neural network in order to enhance the precision and adaptability of English text classification.