Estimating Social Influence from Observational Data

Dhanya Sridhar, Caterina De Bacco, David Blei
Proceedings of the First Conference on Causal Learning and Reasoning, PMLR 177:712-733, 2022.

Abstract

We consider the problem of estimating social influence, the effect that a person’s behavior has on the future behavior of their peers. The key challenge is that shared behavior between friends could be equally explained by influence or by two other confounding factors: 1) latent traits that caused people to both become friends and engage in the behavior, and 2) latent preferences for the behavior. This paper addresses the challenges of estimating social influence with three contributions. First, we formalize social influence as a causal effect, one which requires inferences about hypothetical interventions. Second, we develop Poisson Influence Factorization (PIF), a method for estimating social influence from observational data. PIF fits probabilistic factor models to networks and behavior data to infer variables that serve as substitutes for the confounding latent traits. Third, we develop assumptions under which PIF recovers estimates of social influence. We empirically study PIF with semi-synthetic and real data from Last.fm, and conduct a sensitivity analysis. We find that PIF estimates social influence most accurately compared to related methods and remains robust under some violations of its assumptions.

Cite this Paper

BibTeX
@InProceedings{pmlr-v177-sridhar22a, title = {Estimating Social Influence from Observational Data}, author = {Sridhar, Dhanya and Bacco, Caterina De and Blei, David}, booktitle = {Proceedings of the First Conference on Causal Learning and Reasoning}, pages = {712--733}, year = {2022}, editor = {Schölkopf, Bernhard and Uhler, Caroline and Zhang, Kun}, volume = {177}, series = {Proceedings of Machine Learning Research}, month = {11--13 Apr}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v177/sridhar22a/sridhar22a.pdf}, url = {https://proceedings.mlr.press/v177/sridhar22a.html}, abstract = {We consider the problem of estimating social influence, the effect that a person’s behavior has on the future behavior of their peers. The key challenge is that shared behavior between friends could be equally explained by influence or by two other confounding factors: 1) latent traits that caused people to both become friends and engage in the behavior, and 2) latent preferences for the behavior. This paper addresses the challenges of estimating social influence with three contributions. First, we formalize social influence as a causal effect, one which requires inferences about hypothetical interventions. Second, we develop Poisson Influence Factorization (PIF), a method for estimating social influence from observational data. PIF fits probabilistic factor models to networks and behavior data to infer variables that serve as substitutes for the confounding latent traits. Third, we develop assumptions under which PIF recovers estimates of social influence. We empirically study PIF with semi-synthetic and real data from Last.fm, and conduct a sensitivity analysis. We find that PIF estimates social influence most accurately compared to related methods and remains robust under some violations of its assumptions.} }
Endnote
%0 Conference Paper %T Estimating Social Influence from Observational Data %A Dhanya Sridhar %A Caterina De Bacco %A David Blei %B Proceedings of the First Conference on Causal Learning and Reasoning %C Proceedings of Machine Learning Research %D 2022 %E Bernhard Schölkopf %E Caroline Uhler %E Kun Zhang %F pmlr-v177-sridhar22a %I PMLR %P 712--733 %U https://proceedings.mlr.press/v177/sridhar22a.html %V 177 %X We consider the problem of estimating social influence, the effect that a person’s behavior has on the future behavior of their peers. The key challenge is that shared behavior between friends could be equally explained by influence or by two other confounding factors: 1) latent traits that caused people to both become friends and engage in the behavior, and 2) latent preferences for the behavior. This paper addresses the challenges of estimating social influence with three contributions. First, we formalize social influence as a causal effect, one which requires inferences about hypothetical interventions. Second, we develop Poisson Influence Factorization (PIF), a method for estimating social influence from observational data. PIF fits probabilistic factor models to networks and behavior data to infer variables that serve as substitutes for the confounding latent traits. Third, we develop assumptions under which PIF recovers estimates of social influence. We empirically study PIF with semi-synthetic and real data from Last.fm, and conduct a sensitivity analysis. We find that PIF estimates social influence most accurately compared to related methods and remains robust under some violations of its assumptions.
APA
Sridhar, D., Bacco, C.D. & Blei, D.. (2022). Estimating Social Influence from Observational Data. Proceedings of the First Conference on Causal Learning and Reasoning, in Proceedings of Machine Learning Research 177:712-733 Available from https://proceedings.mlr.press/v177/sridhar22a.html.

Related Material