Analysis of Evolutionary Patterns in Short-Video Content Preferences Based on Audience Behavior Data
Main Article Content
Abstract
User preferences on short-video platforms exhibit dynamic evolutionary characteristics that traditional static recommendation models struggle to capture in terms of drift and abrupt shifts. Based on 32 million user behavior records from a leading platform, this study constructs multi-dimensional feature vectors and proposes an LSTM-based preference drift-and-mutation detection model. Through multi-granularity temporal window dynamic modeling of evolutionary trajectories, the detection accuracy reaches 87.3%, representing a 23.6 percentage point improvement over baseline methods. The study further quantifies the driving mechanisms of content features, social events, and algorithmic interventions, and designs a dynamic recommendation mechanism accordingly. A/B testing results show that user dwell time increased by 18.7% and content diversity improved by 31.2%, providing a theoretical basis and technical pathway for precise recommendation and content ecosystem optimization on short-video platforms.
Downloads
Article Details
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
References
Y. Gu, Z. Xu, and H. Yang, “Prediction Algorithm for Short-Video User Behavior Based on Multi-Task Learning and User Interest Change,” Complex Systems and Complexity Science, vol. 20, no. 4, pp. 69-76, 2023, doi: 10.13306/j.1672-3813.2023.04.010.
Z. Xue and Y. Liu, “Analysis of the Communication Characteristics and Impact of Vertical-Screen Video in a Fragmented Network Context,” Journalism Lover, no. 08, pp. 104-106, 2023, doi: 10.16017/j.cnki.xwahz.2023.08.027.
L. Lin and Y. Ruan, “Platformized Production and Consumption: Short Video as an Affective Medium,” Modern Communication (Journal of Communication University of China), vol. 46, no. 3, pp. 148-160, 2024, doi: 10.19997/j.cnki.xdcb.2024.03.015.
L. Xiao, L. Sun, Z. Lei, et al., “How Do Features in Health Short-Form Videos Impact Viewer Engagement: An Empirical Study,” Industrial Management & Data Systems, vol. 126, no. 2, pp. 678-709, 2026, doi: 10.1108/IMDS-04-2024-0385.
C. Gan, X. Ming, and Z. Yan, “Factors Influencing the Effect of Virtual Digital Human Short Videos in Spreading Traditional Culture: An Empirical Study Based on Douyin,” Library and Information Service, vol. 69, no. 23, pp. 113-124, 2025, doi: 10.13266/j.issn.0252-3116.2025.23.009.
L. Zhang, J. Wu, and K. Chen, “How Do Danmaku Comments Influence the Dissemination and Transmission of Intangible Cultural Heritage-An Interactive Ritual Study of UGC Short Videos on Bilibili,” Journal of Social Science of Hunan Normal University, vol. 54, no. 4, pp. 146-156, 2025, doi: 10.19503/j.cnki.1000-2529.2025.04.016.
Y. Gu, Y. Wang, and H. Yang, “A Multi-Behavior Click Prediction Model for Short-Video Users Based on User Behavior Sequences,” Journal of Electronics & Information Technology, vol. 45, no. 2, pp. 672-679, 2023.
Y. Feng, Y. Sun, H. Xu, et al., “Research on a Real-Time Short-Video Recommendation Method Based on Knowledge Graphs,” Journal of Liaoning University (Natural Science Edition), vol. 50, no. 4, pp. 302-311, 2023, doi: 10.16197/j.cnki.lnunse.2023.04.010.
J. Huang, J. Liu, Z. Ru, et al., “Modeling Evolving User Interests and Engagement on Short Video Sharing Platforms: An Attention-Based Deep Generative Approach,” Decision Support Systems, vol. 203, Art. no. 114629, 2026, doi: 10.1016/j.dss.2026.114629.
D. Zhu, “Optimizing the User Personalized Recommendation System of New Media Short Videos by Using Machine Learning,” Journal of Computational Methods in Sciences and Engineering, vol. 25, no. 5, pp. 4787-4801, 2025, doi: 10.1177/14727978251341490.
Z. Shengtai, Y. Yang, and Y. Yiwei, “Investigation of Users Information Adoption Intention in Short Video Applications: A Perspective on Flow Experience,” Journal of Theoretical and Applied Electronic Commerce Research, vol. 20, no. 2, pp. 91, 2025, doi: 10.3390/jtaer20020091.
Z. Hengmin, W. Hongcheng, and W. Jing, “Understanding Users Information Dissemination Behaviors on Douyin, a Short Video Mobile Application in China,” Multimedia Tools and Applications, vol. 83, no. 20, pp. 58225-58243, 2023, doi: 10.1007/s11042-023-17831-3.
W. Liu, H. Wan, and B. Yan, “Short Video Recommendation Algorithm Incorporating Temporal Contextual Information and User Context,” Computer Modeling in Engineering & Sciences, vol. 135, no. 1, pp. 239-258, 2022, doi: 10.32604/cmes.2022.022827.
J. Zhang and Y. Liu, “Examination of the Filter Bubble in Short Videos Under Algorithmic Recommendation Technology and Its Legal Regulation,” Tribune of Study, no. 4, pp. 128-136, 2025, doi: 10.16133/j.cnki.xxlt.2025.04.001.
Y. Pan, Z. Yang, H. Tang, et al., “User Circle-Breaking Analysis in the Short-Video Platform Ecosystem Based on Large Language Models-A Case Study of Kuaishou,” Library and Information Service, vol. 69, no. 4, pp. 34-52, 2025, doi: 10.13266/j.issn.0252-3116.2025.04.004.
S. Zhang, A. Wang, and H. Chen, “Indifferent Dependency and Immersive Experience: Research on the Continued Use Intention of Mobile Short-Video Users,” Library and Information Service, vol. 66, no. 14, pp. 89-100, 2022, doi: 10.13266/j.issn.0252-3116.2022.14.010.