Emerging Focus in Chinese Literary Study (1927 to 2023): Latent Dirichlet Allocation (LDA) Based Topic Modeling Analysis

Literature has vital historical values that reveal the truth of culture, ideology of people, political focus, and human experiences like a series of no-photo films via a combination of flat words. As the carrier of history, literature plays like one decent clerk who recorded the historical presentation of modern China through a proliferation of scholarly articles. This study aims to provide a comprehensive overview of the emerging focus of modern Chinese literary research with the Latent Dirichlet Allocation (LDA) topic model to explore the research themes and trends of former researchers from 1927 to 2023. LDA is a text-mining-based approach utilized to reveal principal themes from a substantial dataset of short textual documents. A total of 14,148 articles published between 1927 and October 2023 were collected and analyzed. Findings suggest that the primary scholarly focus areas of CNKI have been significantly influenced by historical events and foreign cultures, notably the Soviet Union and America. Over the past decades, the research trend has also shifted from revolution, Chinese ambient culture, and Soviet literature to American literature, gender, digital tools, and global issues. The primary research themes and new trends identified by LDA are instrumental in aiding researchers in discerning contemporary research questions and making more informed decisions. The findings of this research could be utilized in complementarily exploring the ideology of Chinese people in different periods.