Text Data Analysis in Chinese Folk Music with Effective Clustering Model toward Feature Identification of Inheritance

Abstract

Folk music based on big data analysis can provide valuable insights into the history, culture, and evolution of traditional music. By understanding the historical and cultural contexts of folk music, one better appreciate its value and contribute to its continued development and inheritance. Big data analysis can help identify patterns and trends in the performance, distribution, and reception of folk music across time and space. In this paper designed a Weighted Clustering Euclidean Feature (WCEF) model to evaluate folk music on the development of inheritance. Initially, the text data is extracted from folk music for the estimation of features in the big data analysis. Secondly, the WCEF model uses a clustering model for a subset of the folk music dataset with Weighted Non-Negative Matrix Factorization (WNMF). With the clustered model feature extraction is computed with Named Entity Recognition (NER). The NER model uses the Euclidean distance estimation for the computation of features in the folk data analysis. Finally, the WCEF model uses the deep learning model for the classification of inheritance in folk music. The experimental analysis stated that the WCEF model effectively classifies the folk music words and their contribution to inheritance.