School of Science, China University of Geosciences, Beijing 100083, China
Nowadays, music has become an inseparable part of our lives, and studying the history of music can also helps us analyze the historical environment of the society at that time. To study the history of music is to analysis the characteristics and vocals of music, as well as data on the ability of influence among artists. Our paper attempts to establish a model that can analyze and evaluate the influence and similarity of musicians and their works to further study the history of music. We use cosine correlation to analyze the correlation of all music and music characteristics. Then we exclude a few sets of data that have little to do with popularity, and perform dimensionality reduction of the data. Then the cosine similarity is used to calculate the similarity of different genres, and the similarity between the internal genres and the artists represented by the genres. Finally, it is concluded that artists are more similar in genres. Moreover, we found through calculations: Within the genre, most of the characteristics have not changed much, but we can see their small changing trends. For example, the changing trend within the rock genre is changing from focusing on lyrics to focusing on musical melody. Another finding is that the artist is not necessarily in the same genre as the artists he follows, but the similarity of the works of the artist and the similarity of the artists he follows are basically relatively high. It can be seen that the artist with a higher influence score is he Generally speaking, the works of "infectiousness" are relatively high. In addition, we also verify the stability by calculating the variance of the data in the similarity model, and the results obtained are between 0.09 and 0.20, which proves that the stability of our model is relatively high.
Network Science, Music, Cosine Similarity, Influence
Shiyi Hao. Research on Music Characteristics and Artist Influence. Frontiers in Art Research (2021) Vol. 3, Issue 2: 55-59. https://doi.org/10.25236/FAR.2021.030211.
 Tang, P.; Song, C.; Ding, W.; Ma, J.; Dong, J.; Huang, L. Research on the Node Importance of a Weighted Network Based on the K-Order Propagation Number Algorithm. Entropy 2020, 22, 364.
 Lukun Zheng. Using mutual information as a cocitation similarity measure. 2019, 119(3):1695-1713.
 Zhou Xuan, Zhang Fengming, Zhou Weiping, Zou Wei, Yang Fan.Evaluation of functional robustness of complex networks using node efficiency [J]. Acta Physica Sinica, 2012, 61(19): 1-7.
 Research on Information Extraction Technology for Music Field [D]. Guangdong: South China University of Technology, 2019