Communications in Humanities Research ISSN: 2753-7072
Home> Volumes> Volume CHR Vol.52> Article
Research Article

Popularity Prediction of Bilibili Videos: Analysis of the Top Creators' Contents in 2023

Jian ZhengNortheastern University (China)*

* Corresponding author: [email protected]

Abstract

With the rise of video content platforms, Bilibili has become a major platform in China. By using data from 600 videos by top creators in 2023, this study examines the factors influencing video popularity on Bilibili. Key engagement metrics, such as bullet comments, likes and shares are analyzed alongside 3,576 comments for sentiment polarity. The analysis reveals a complex relationship between content characteristics and video popularity, providing insights for content optimization. The analysis demonstrates that certain content features, like the number of bullet comments and positive viewer sentiment, have a stronger impact on video popularity. However, other features, such as likes and shares, though reflective of user appreciation, show weaker correlations with actual view counts. This suggests that while multiple content characteristics influence engagement, not all have an equal or direct effect on driving video views.

Keywords: Bilibili; Video popularity; Engagement behavior; Sentiment analysis; Bullet comments
Published: December 31, 2024
DOI: 10.54254/2753-7064/2024.19111
Volume: CHR Vol.52
pp. 176-180
Download PDF

References

  1. Jie, X., Yong, Z. (2022) Understanding user engagement on video-sharing platforms: A study on Bilibili. Journal of Social Media Studies, 35: 14–25.
  2. [Wei, L., Qiang, S. (2021) The impact of interactive features on user engagement in social media videos. Media & Communication Research, 47: 78–89.
  3. Yong, C., Xia, L. (2020) Analyzing the role of bullet comments in video platforms: The case of Bilibili. New Media Research, 29: 102–110.
  4. Hua, Z., Rui, W. (2019) Video content analysis and prediction models in social media. Computational Social Science Journal, 22: 132–140.
  5. Sang, L., Min, K. (2020) Social influence and content engagement on video-sharing platforms. International Journal of Digital Media, 18: 55–68.
  6. Zhi, L., Lei, T. (2021) Predicting video virality using machine learning: A case study on Bilibili. Journal of Data Science and Analytics, 9: 44–58.
  7. Hao, Z., Jing, M. (2023) Sentiment analysis in user-generated content: Insights from Bilibili comments. Journal of Artificial Intelligence Research, 17: 89–102.
  8. Lin, C., Jun, W. (2020) Factors influencing user engagement on video-sharing platforms: A case study on Bilibili. Journal of Digital Media and Society, 15(3), 87–102.
  9. Yi, H., Shan, Z. (2021) The role of sentiment analysis in predicting video popularity on social media platforms. International Journal of Data Science and Analytics, 12(1), 45–58.
  10. Jian, W., Xin, L. (2022) Exploring the correlation between user sentiment and content performance on Chinese video-sharing platforms. New Media & Society, 24(5), 65–80.