Analysis of Chinese classical literature texts and prediction of internet language trends based on natural language processing

Abstract

Chinese classical literature refers to ancient texts that represent China’s philosophical, historical, and cultural heritage. Chinese classical literature texts and the internet language trends were investigated with NLP that demonstrate the evolution of cultural, along with the linguistic shifts, and current communication methods. The purpose of this research is to analyze the Chinese classical literature texts and to predict the internet language trends using NLP techniques. To begin with, the ancient Chinese text data have been collected from Kaggle. In addition, text cleaning, tokenization, stop word removal, stemming, and lemmatization are applied for text preprocessing. Then, text representation and N-Grams Analysis are utilized for feature extraction. Furthermore, the present investigation employs analytical techniques that contain Chinese classical literature and trend prediction. LDA and sentiment analysis has been employed for the Chinese classical literature, and elevated LSTM is used for trend prediction. Lastly, the topic modeling outcomes, sentiment analysis of ancient Chinese texts, elevated LSTM model performance, and trends in language usage over time are utilized for analyzing the performance. This research utilizes some metrics for analyzing the performance of elevated LSTM. The results of elevated LSTM model performance are 0.92 accuracy, 0.89 precision, 0.91 recall, and 0.90 F1-score. This investigation efficiently analyzes the Chinese classical literature and predicts the internet language trends by using the NLP techniques which demonstrate important insights into historical themes and modern language trends.