Abstract
Vast volumes of data are produced from numerous sources, including websites and social media. It is necessary to extract significant information from text data, categorize it, and forecast end-user behavior or emotions. Natural-language processing research on text categorization is an example of a topic that organizes unstructured text input into useful category classifications. The Bi-Directional Long Short-Term Memory (Bi-LSTM) model, which has recently been used to a number of natural language processing (NLP) applications, is being employed in this study to classify sentences. LSTM models are more suited for text classification because they can capture long-term dependencies between word sequences. Our suggested approach performs better than the current Machine Learning models.
doi: 10.17756/nwj.2023-s4-070
Citation: Basha SM, Balemla A, Anjum S, Ramesh A. 2023. Nanoscale Text Classification with Bi-LSTM: Enhancing Precision. NanoWorld J 9(S4): S417-S420.