What Do Chinese Folk Singers Really Sing? A Python Text‑Mining Journey

Using Python, the author scraped approximately 150,000 folk song lyrics from NetEase Cloud Music and performed a series of analyses to uncover the themes and preferences of Chinese folk singers.

Data Collection

The lyrics were obtained with two Python scripts for crawling lyrics and songs, as described in earlier articles.

Word Segmentation and Frequency

Jieba was employed to segment the Chinese text and calculate word frequencies. The main code snippet is shown in the accompanying image. /* code omitted – see image */ The resulting frequencies were exported to Excel and visualized with a word cloud.

Season Preference

A pie chart shows that folk singers favor spring the most, followed by winter.

Preferred Day

Bar‑chart analysis indicates a strong preference for “tomorrow,” reflecting optimism about the future.

City Preference

Geographical word‑frequency shows Beijing dominates, while Chengdu, Nanjing, Shanghai, and Kunming also appear.

North vs South

Comparison reveals a slight preference for southern cities and “southern girls.”

Sentiment Analysis

SnowNLP was used to assess sentiment; results show generally upbeat emotions, with some artists like Xu Wei being more energetic and others more mellow.

Overall, the analysis suggests folk singers frequently mention youth, hope, and the passage of time, favor spring and winter, look forward to tomorrow, love Beijing yet cherish southern cities like Chengdu, and maintain a generally positive emotional tone.