Peeking Strategy for Online News Diffusion Prediction Via Machine Learning

25 Pages Posted: 17 Feb 2022

See all articles by Yaotian Zhang

Yaotian Zhang

Nanjing University

Keke Shang

Nanjing University

Mingming Feng

Fudan University

Yijun Ran

Southwest University

Cheng-Jun Wang

Nanjing University

Abstract

For computational social scientists, cascade size prediction and fake news detection are two primary problems in news diffusion or computational mass communication research. Previous studies predict news diffusion via peeking the social process (temporal structure) data in the initial stage, which is summarized as Peeking strategy. However, the combination of peeking strategies and machine learning algorithms has not been fully investigated. To predict cascade size and detect false news, we adopt Peeking strategy based on well-known machine learning algorithms. Our results show that Peeking strategy can effectively improve the accuracy of cascade size prediction. Meanwhile, we can peek into a smaller time window to achieve a high performance in predicting the cascade size compared with previous methods. Nevertheless, we find that Peeking strategy with network structures fails in significantly improving the performance of false news detection. Finally, we argue that cascade structure properties can aid in prediction of cascade size, but not for the false news detection.

Keywords: News Diffusion, Tree-like Network, Peeking strategy, Cascade Structure

Suggested Citation

Zhang, Yaotian and Shang, Keke and Feng, Mingming and Ran, Yijun and Wang, Cheng-Jun, Peeking Strategy for Online News Diffusion Prediction Via Machine Learning. Available at SSRN: https://ssrn.com/abstract=4025009 or http://dx.doi.org/10.2139/ssrn.4025009

Yaotian Zhang

Nanjing University ( email )

Nanjing
China

Keke Shang (Contact Author)

Nanjing University ( email )

Nanjing
China

Mingming Feng

Fudan University ( email )

Beijing West District Baiyun Load 10th
Shanghai, 100045
China

Yijun Ran

Southwest University ( email )

College of Economics and Management
Chongqing, 400715
China

Cheng-Jun Wang

Nanjing University ( email )

Nanjing
China

Do you have negative results from your research you’d like to share?

Paper statistics

Downloads
38
Abstract Views
210
PlumX Metrics