Sentiment Analysis of Modern Chinese Literature Based on Deep Learning

Abstract

Recent advancements in deep learning have facilitated sentiment analysis of modern Chinese literature. By leveraging techniques such as recurrent neural networks (RNNs) and transformer models like BERT, researchers can effectively gauge the sentiment expressed within literary texts. These models learn intricate patterns and context-specific nuances, enabling them to discern the emotional tone of Chinese literature accurately.Sentiment analysis, a crucial task in natural language processing, plays a pivotal role in understanding human emotions and opinions expressed in textual data. In this paper, we propose a novel deep learning framework, termed BERT-LLSTM-DL, for sentiment analysis in Chinese literature. The framework integrates Bidirectional Encoder Representations from Transformers (BERT) for language representation, Long Short-Term Memory (LSTM) networks for sequential learning, and deep learning techniques for feature extraction. We evaluate the proposed model on a dataset comprising Chinese literature texts and achieve promising results in terms of accuracy, precision, recall, and F1-score.