Article: Sports social media influence prediction model with temporal transformer and causal reasoning Journal: International Journal of Information and Communication Technology (IJICT) 2026 Vol.27 No.44 pp.90 - 112 Abstract: Predicting the spread of information in sports social media remains challenging due to the complex interplay between dynamic propagation processes and confounding contextual factors. To move beyond purely correlation-driven approaches, this paper proposes a novel twin-stream temporal transformer architecture integrated with a causal inference module. This model concurrently encodes sequences of match events and social media propagation states, while a counterfactual reasoning component adjusts for potential confounders. Evaluated on a real-world dataset from professional soccer, our framework achieves a root mean square error of 0.412, a mean absolute error of 0.298, and an area under the curve of 0.891, outperforming existing benchmarks by 6.3% to 14.7% across key metrics. The model not only enhances predictive accuracy but also quantifies the causal effect of specific match events, offering both robust forecasting and explainable insights into the drivers of social media engagement. Inderscience Publishers - linking academia, business and industry through research

Title: Sports social media influence prediction model with temporal transformer and causal reasoning

Authors: Li Zhang

Addresses: School of Journalism and Communication, Chengdu Sport University, Chengdu, 641400, China

Abstract: Predicting the spread of information in sports social media remains challenging due to the complex interplay between dynamic propagation processes and confounding contextual factors. To move beyond purely correlation-driven approaches, this paper proposes a novel twin-stream temporal transformer architecture integrated with a causal inference module. This model concurrently encodes sequences of match events and social media propagation states, while a counterfactual reasoning component adjusts for potential confounders. Evaluated on a real-world dataset from professional soccer, our framework achieves a root mean square error of 0.412, a mean absolute error of 0.298, and an area under the curve of 0.891, outperforming existing benchmarks by 6.3% to 14.7% across key metrics. The model not only enhances predictive accuracy but also quantifies the causal effect of specific match events, offering both robust forecasting and explainable insights into the drivers of social media engagement.

Keywords: social media influence prediction; temporal transformer; causal inference; sports analytics; information diffusion.

DOI: 10.1504/IJICT.2026.153389

International Journal of Information and Communication Technology, 2026 Vol.27 No.44, pp.90 - 112

Received: 27 Dec 2025
Accepted: 31 Jan 2026
Published online: 06 May 2026 *

Title: Sports social media influence prediction model with temporal transformer and causal reasoning

Keep up-to-date