Prediction On Tiktok Like Behavior Based on Random Forest Model

Ying Nie; Yundong Xu

doi:10.54097/d6metn07

Authors

Ying Nie
Yundong Xu

DOI:

https://doi.org/10.54097/d6metn07

Keywords:

TikTok, Like Behavior, Prediction, Random Forest Model.

Abstract

In recent years, the TikTok short video platform has rapidly ascended, attracting a plethora of users to participate in content creation and interaction. Predicting 'like' behavior delves deeply into user preferences, offering reference value for the platform to enhance traffic. Based on this, the present paper focuses on TikTok 'like' behavior as the research subject and employs a Random Forest model for its prediction. The model's fit was enhanced by optimizing the number of estimators (n_e) and the maximum number of features considered for splitting a node (max_f), aiming to provide a beneficial reference for TikTok and other social media platforms atop optimizing existing research. The results demonstrate that the fitted model boasts a commendable predictive performance, with an accuracy of 99.07%. The application of the model will aid the TikTok short video platform and other platforms in making informed video recommendations to users, thus improving the user experience.

Downloads

Download data is not yet available.

References

Lü Wenbao. Analysis of Characteristics of Highly Liked Short Videos on Mainstream Media's TikTok Accounts: A Case Study of COVID-19 Prevention and Control Videos by Three Mainstream Media Outlets[J]. Media, 2021, (15): 53-55.

Zhang Yu, Zhao Haobo. A Multidimensional Study of 'Like' Behavior in Social Media[J]. Journal for News Buffs, 2017, (08): 8-11. DOI: 10.16017/j.cnki.xwahz.2017.08.003

Hu Xian, Wu Jiang, Liu Kaiyu, et al. Study on the Factors Influencing 'Like' Social Interaction Behavior: Based on the Context of WeChat Moments[J]. Information Science, 2020, 38(01): 36-41. DOI: 10.13833/j.issn.1007-7634.2020.01.006.

Lu Zeyu, Zha Xianjin, Yan Yalan. Study on the Influence Mechanism of 'Like' Behavior for Intelligent Recommendation Content in Social Media Environments[J]. Modern Information, 2023, 43(02): 42-55.

Yan Xinmiao, Sun Taolan, Lu Yuhang, et al. A Machine Learning-based Prediction Model for Dental Caries in 12-year-old Children in Sichuan Province[J]. West China Journal of Stomatology, 2023, 41(06): 686-693.

Zhang Fangfeng, Ni Ran. Research on Online User Consumption Prediction Model Based on SOMTE Balance[J]. Mathematics in Practice and Theory, 2020, 50(15): 49-59.

Zhong Minhui, Zhang Runa, Yu Chan, et al. Construction and Validation of a Predictive Model for Postpartum Depression Risk[J]. Journal of Nursing, 2023, 38(15): 76-81.

Hu Yanfang, Xiong Wen, Gao Wei. A Method for Predicting User Churn in Online Games Based on the Spark Platform[J]. Computer Engineering and Science, 2022, 44(10): 1730-1737.

Shen Jinglei, Yu Huiqun, Fan Guisheng, et al. Design and Implementation of a Recommendation System Based on Random Forest Algorithm[J]. Computer Science, 2017, 44(11): 164-167+186.

Wu Lihua, Wang Zhaojun, Chi Qinghua, et al. Prediction of Opportunistic Connections in Mobile Internet Based on User Behavior[J]. Journal of Wuhan University (Engineering Edition), 2019, 52(01): 89-94.

Gui Jinyong, Li Shengjun, Gao Jianhu, et al. A Random Forest Prediction Method for Gas Saturation Based on Feature Variable Expansion[J/OL]. Lithologic Reservoirs, 1-11 [2024-01-06].

Wang Xiaozhi, Mou Fengyun, Zhang Yongchuan, et al. Short-term Traffic Flow Prediction Using Taxi GPS Trajectory Data: A Case Study of the Jiefangbei District in Chongqing City[J]. Science Technology and Engineering, 2023, 23(28): 12265-12274.

BREIMAN L. Random forests［J］. Machine Learning, 2001, 45(1): 5-32.