Year: 2025
Type: article
Abstract: Efficient and accurate categorization of Chinese books in digital libraries is still a challenge, and traditional manual methods are difficult to cope with the huge number of books.In this study, a novel Chinese book classification model based on an enhanced BERT architecture is proposed, which contains a pre-trained language model (PLM) and a long-short-time convolutional neural network (LCN) for improved feature extraction.Experimental results showed that the model achieved up to 93.6% for Micro F1, 95.3% for Macro F1, 90% for Mac-P, and 91% for Mic-P with an input text length of 256 and a batch size of 32.The results illustrate the model's efficacy in Chinese book classification, offering theoretical advancements in natural language processing applications and practical enhancements in library resource management and user services.
Authors: Lu, Ke, Zheng, Bei, Shi, Jingjing
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: gold
Estimated APC paid: $431
OpenAlex ID: W4410046502