Author(s)

ZhiYang Chen^1*, JiaXin Wu²

Affiliation(s)

¹School of Mathematics and Physics, Southwest University of Science and Technology, Mianyang 621000, Sichuan, China.

²School of Law, Southwest University of Science and Technology, Mianyang 621000, Sichuan, China.

Corresponding Author

ZhiYang Chen

ABSTRACT

This study addresses user interaction dynamics on social media platforms by constructing separate models for predicting new follower counts for bloggers and classifying users' targeted following behavior. Quantitative analysis of new follower counts reveals a high correlation between interaction behavior and follower growth, with correlation coefficients exceeding 0.89. By constructing an XGBoost model that utilizes second-order Taylor series expansion to optimize the objective function and incorporates 1- to 3-day lagged features to capture time-series patterns, the model demonstrated robust performance on the test set with an average absolute error of 20.71. For the user targeted following behavior classification prediction, a Random Forest model was selected to address the low-dimensionality and strong nonlinearity of the features. The study employed target encoding strategies to smooth user and blogger IDs, preventing overfitting, and defined interaction intensity formulas based on behavior weights. Experimental results show the Random Forest model achieved an AUC of 0.83 and an F1 score of 74.25% in user follow prediction tasks, effectively enhancing behavioral prediction accuracy. This study provides quantitative insights into user growth dynamics and micro-interaction patterns on social platforms through ensemble learning algorithms.

KEYWORDS

Social media user behavior; XGBoost algorithm; Random forest model

CITE THIS PAPER

ZhiYang Chen, JiaXin Wu. Predicting follower growth for social media bloggers and modeling user following behavior using XGBoost and random forest ensemble learning. World Journal of Information Technology. 2026, 4(1): 25-32. DOI: https://doi.org/10.61784/wjit3079.

REFERENCES

[1] Su J, Luo X, Li H, et al. Unlocking the Power of User Tie Strength: A Multistudy on Cross-Platform Content Sharing Behaviors. Journal of the Association for Information Systems, 2025, 26(5): 1457-1484. DOI: 10.17705/1JAIS.00942.

[2] Wan S, Yang S, Fu Z. Focus on user micro multi-behavioral states: Time-sensitive User Behavior Conversion Prediction and Multi-view Reinforcement Learning Based Recommendation Approach. Information Processing and Management, 2025, 62(2): 103967-103967. DOI: 10.1016/j.ipm.2024.103967.

[3] Meier Y, Kramer C N. A longitudinal examination of Internet users' privacy protection behaviors in relation to their perceived collective value of privacy and individual privacy concerns. New Media & Society, 2024, 26(10): 5942-5961. DOI: 10.1177/14614448221142799.

[4] Saura R J, Marqués P D, Soriano R D. Privacy concerns in social media UGC communities: Understanding user behavior sentiments in complex networks. Information Systems and e-Business Management, 2023, 23(1): 1-21. DOI: 10.1007/s10257-023-00631-5.

[5] E I X W, Zhang Q. The online website privacy disclosure behavior of users based on concerns-outcomes model. Soft Computing, 2022, 26(21): 11733-11747. DOI: 10.1007/s00500-022-07369-1.

[6] Park M, Chai S. Establish a Model for Detecting Fake News Using Machine Learning; Focusing on User Behaviors and Social Networks. Proceedings of the Korean Society for Intelligent Information Systems Conference, 2022.

[7] Yang Q, Gao L. Research on the Influence of Privacy Concern and Relationship Quality on User Value Co-Creation Behavior of Tourism Platform. Journal of Social Science and Humanities, 2022, 4(4). DOI: 10.53469/jssh.2022.4(04).18.

[8] Meriem A. The Internet user relational orientation: towards a better understanding of online browsing behaviour. Journal of Marketing Management, 2021, 37(13-14): 1374-1408. DOI: 10.1080/0267257x.2021.1917644.

[9] Jennifer G, Jennifer H, Megan P, et al. The mediating effect of meditation and physical activity behaviors on the associations of COVID-19 related worry, attention to news, and stress with mental health in mobile app users in the United States: Cross-sectional survey. JMIR Mental Health, 2021, 8(4): e28479. DOI: 10.2196/28479.

[10] Lauren C, Colette M. A qualitative systematic review of Early Intervention in Psychosis service user perspectives regarding valued aspects of treatment with a focus on cognitive behavioural therapy. The Cognitive Behaviour Therapist, 2021, 14: e31. DOI: 10.1017/s1754470x2100026x.