An Automated Grading System for Competition Theses Assisted by NLP Models

As the digital transformation of education continues to advance, the inefficiency and subjectivity of traditional manual scoring methods have become increasingly prominent. To address this issue, this study developed an automated scoring process. The process includes several key steps: reading text files, training latent Dirichlet allocation (LDA) topic models, matching texts with conditional sentence libraries, and performing natural language processing (NLP) analysis. The scoring method used in this study follows the standards proposed by advocates of text scoring conditions to comprehensively evaluate the completeness and accuracy of the text. The entire paper is comprehensively evaluated from four dimensions: completeness, content, summary quality, and writing ability.