Optimization of Data Mining and Analysis System for Chinese Language Teaching Based on Convolutional Neural Network.

Area of Science:

• Computational Linguistics
• Educational Technology
• Data Mining

Background:

• Chinese language is integral to understanding and preserving traditional Chinese culture.
• Effective Chinese language teaching is crucial for cultural inheritance and development.
• Big data analytics offers opportunities to improve teaching methodologies and outcomes.

Purpose of the Study:

• To propose and evaluate a text clustering method for Chinese language teaching data using big data analytics.
• To develop and optimize a data mining and analysis system for Chinese language education.
• To enhance the depth and comprehensiveness of Chinese character data mining in educational contexts.

Main Methods:

• Application of text clustering technology for analyzing and categorizing Chinese language teaching data.
• Integration of convolutional neural network (CNN) and K-means algorithm for text clustering.
• Development and optimization of a big data-driven Chinese language teaching data mining analysis system.

Main Results:

• The optimized K-means algorithm achieved target accuracy in 683 iterations.
• The optimized system demonstrated a higher average K-measure value (0.770) compared to the original system.
• The K-means algorithm significantly improved clustering effectiveness and data mining capabilities.

Conclusions:

• The proposed CNN and K-means based text clustering method effectively mines Chinese language teaching data.
• The optimized data mining analysis system enhances the quality of Chinese language teaching.
• This approach supports the deeper understanding and promotion of Chinese language and culture.