A1 Journal article (refereed)
Estimating the causal effect of timing on the reach of social media posts (2023)

Valkonen, L., Helske, J., & Karvanen, J. (2023). Estimating the causal effect of timing on the reach of social media posts. Statistical Methods and Applications, 32, 493-507. https://doi.org/10.1007/s10260-022-00664-z

JYU authors or editors

Publication details

All authors or editors: Valkonen, Lauri; Helske, Jouni; Karvanen, Juha

Journal or series: Statistical Methods and Applications

ISSN: 1618-2510

eISSN: 1613-981X

Publication year: 2023

Publication date: 24/10/2022

Volume: 32

Pages range: 493-507

Publisher: Springer Science and Business Media LLC

Publication country: Germany

Publication language: English

DOI: https://doi.org/10.1007/s10260-022-00664-z

Publication open access: Openly available

Publication channel open access: Partially open access channel

Publication is parallel published (JYX): https://jyx.jyu.fi/handle/123456789/83774

Abstract

Modern companies regularly use social media to communicate with their customers. In addition to the content, the reach of a social media post may depend on the season, the day of the week, and the time of the day. We consider optimizing the timing of Facebook posts by a large Finnish consumers’ cooperative using historical data on previous posts and their reach. The content and the timing of the posts reflect the marketing strategy of the cooperative. These choices affect the reach of a post via a dynamic process where the reactions of users make the post more visible to others. We describe the causal relations of the social media publishing in the form of a directed acyclic graph, use an identification algorithm to obtain a formula for the causal effect, and finally estimate the required conditional probabilities with Bayesian generalized additive models. As a result, we obtain estimates for the expected reach of a post for alternative timings.

Keywords: marketing communication; social media; Facebook; timing; optimisation; causality; statistical models; Bayesian analysis

Contributing organizations

Related projects

Ministry reporting: Yes

Reporting Year: 2022

JUFO rating: 1