Answers are grounded in this paper and cite their sources.
Bilibili video website has grown into a giant video platform. With the anime culture that can attract the younger generation, Bilibili has built a large-scale user creation platform. To stimulate users’ creative inspiration, Bilibili issued several plans to provide corresponding rewards for the content produced by video creators, attracting more and more people to participate in the creative party. In this context, many excellent works were born, but at the same time, there are also works with mixed qualities in the video, i.e., “low-innovation” works. "Low-innovation" works hinder personal development and have a bad impact on the production climate of the platform. First, this paper uses the principal component analysis algorithm to pre-process the user data of Bilibili to improve the efficiency of the algorithm. Based on the K-means clustering algorithm, it analyzes and identifies "low-innovation" users. According to the analysis results, it sets different incentive plans for different types of user groups and plays a positive role in the video quality of Bilibili.
No takes yet. Share an insight, caveat, or question.
Liu et al. (2023) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: