Ou, Yifan, Gong, Chen, Sun, Feifei, Tan, Cheng, Zhang, Haoran and Zhang, Mengyang (2025) Analyzing user behavior in online communities using data crawling and machine learning algorithms. Proceedings of SPIE - The International Society for Optical Engineering, 13629. ISSN 0277-786X
Full text not available from this repository.Abstract
The rapid growth of online communities as knowledge-sharing platforms has led to an unprecedented influx of user-generated content, posing challenges such as information overload and dynamic changes in user interests. Understanding user behavior patterns is critical for optimizing personalized recommendations, enhancing community engagement, and improving knowledge dissemination. This study adopts an interdisciplinary approach by integrating data crawling techniques and machine learning algorithms to analyze user behavior in online communities. A distributed multi-process Python crawler is designed to collect real-time data efficiently, enabling the construction of a community label network. By extracting both network structural features and statistical attribute features, this study develops a machine learning-based label popularity prediction model to analyze user interest transfer patterns and forecast emerging topic trends. The model is validated through extensive experiments, demonstrating its effectiveness in accurately predicting label popularity and capturing dynamic user behavior shifts. The results highlight the utility of combining data science, network analysis, and machine learning in understanding complex user interactions and optimizing digital community management. This interdisciplinary approach not only enhances the accuracy of trend prediction but also offers new insights into user behavior analysis, contributing to the development of more intelligent and adaptive online knowledge-sharing platforms.
| Item Type: | Article |
|---|---|
| Additional Information: | © 2025 SPIE |
| Divisions: | LSE |
| Subjects: | Q Science > Q Science (General) |
| Date Deposited: | 10 Jun 2025 17:39 |
| Last Modified: | 10 Jun 2025 17:42 |
| URI: | http://eprints.lse.ac.uk/id/eprint/128347 |
Actions (login required)
 |
View Item |
