YouTube View Counts for Chinese Short-Form Dramas with Channel and Timing Features

Chinese short-form dramas on YouTube are analyzed in a dataset of 895 videos uploaded between April and October 2025. The data, uploaded by Yunqiu Yan, includes channel subscriber base size, video duration, and upload timing to model predictors of cumulative view counts. Linear regression, multilayer perceptron, and random forest models were used, with the random forest achieving an R² of 0.666.

Use Cases

• Modeling video view accumulation based on channel subscriber base size.
• Analyzing the association between video duration and attention outcomes.
• Investigating the impact of upload hour on view count performance.
• Comparing the predictive power of linear and non-linear models (e.g., random forest) for platform metrics.

Strengths

• Dataset contains 895 video records, providing a substantive sample for analysis.
• Analysis employs multiple modeling techniques, with the random forest model achieving a test R² of 0.666.
• Clear temporal scope covering uploads from April to October 2025.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count for the underlying raw data is unknown, which may limit suitability assessment.
• Data may reflect geographic and platform bias inherent to its specific source on YouTube.

Provenance

Source

Yunqiu Yan via figshare.

Collection Method

Likely collected via YouTube API or web scraping, as described in the study.

Time Range

April 2025 to October 2025.

Freshness

Last updated 2026-05-22 04:28:04; freshness should be verified.

Geography

Focus on Chinese short-form dramas distributed on the global YouTube platform.