Research on User Profile of Knowledge Video - Taking Bilibili as an Example
- DOI
- 10.2991/978-2-38476-281-1_33How to use a DOI?
- Keywords
- B station platform; knowledge-based video content; user profile construction; textual analysis
- Abstract
Constructing user profiles from relevant information and textual features in the comment sections of the B station platform enables the platform to understand user needs and preferences, thereby improving content, services, and enabling more precise marketing. From each subcategory under the knowledge-based video category, 8 sample videos were selected, yielding 152,823 comments from 104,811 users. These comments were statistically analyzed across various dimensions, including emotional characteristics derived through sentiment analysis. User groups were then clustered based on the similarity values and textual themes of the comments, using text similarity analysis. Based on the clustering results and additional features, user groups were categorized into three distinct segments, whose characteristics were visualized using word cloud diagrams.
- Copyright
- © 2024 The Author(s)
- Open Access
- Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.
Cite this article
TY - CONF AU - Donghong Yang AU - Luyao Guo PY - 2024 DA - 2024/08/31 TI - Research on User Profile of Knowledge Video - Taking Bilibili as an Example BT - Proceedings of the 2024 International Conference on Humanities, Arts, and Cultural Industry Development (HACID 2024) PB - Atlantis Press SP - 274 EP - 280 SN - 2352-5398 UR - https://doi.org/10.2991/978-2-38476-281-1_33 DO - 10.2991/978-2-38476-281-1_33 ID - Yang2024 ER -