Deep Dive into Document Classification: Fusion of RNN and LSTM Approach

Abstract

Deep learning models have transformed text classification, outperforming traditional machine learning in tasks like sentiment analysis, news categorization, and question answering. Among them, Recurrent Neural Networks (RNNs) and Long Short-Term Memory (LSTM) networks excel in handling sequential data. While RNNs capture context well, they struggle with long-term dependencies due to the vanishing gradient problem. LSTMs overcome this with memory cells that retain essential information, making them more effective for tasks requiring long-range context understanding. LSTMs solve this by using memory cells, allowing them to retain context over time. In this paper, we explore different deep learning models, particularly merge RNN and LSTM, to identify the most accurate approach for text and document classification.