Belief Polarization in a Complex World: A Learning Theory Perspective

26 Pages Posted: 15 Jun 2020

See all articles by Nika Haghtalab

Nika Haghtalab

Cornell University

Matthew O. Jackson

Stanford University - Department of Economics; Santa Fe Institute

Ariel Procaccia

Harvard University

Date Written: May 20, 2020


We present two models of how people form beliefs that are based on machine learning theory.

We illustrate how these models shed new insight into observed human phenomena by showing how polarized beliefs can arise even when people are exposed to almost identical sources of information. In our first model, people form beliefs that are deterministic functions that best fit their past data (training sets). In that model, their inability to form probabilistic beliefs can lead people to have opposing views even if their data are drawn from distributions that only slightly disagree. In the second model, people pay a cost that is increasing in the complexity of the function that represents their beliefs. In this second model, even with large training sets drawn from exactly the same distribution, agents can disagree substantially because they simplify the world along different dimensions. We discuss what these models of belief formation suggest for improving people's accuracy and agreement.

Keywords: Learning Theory, Belief Formation, Polarization, Machine Learning

JEL Classification: D83, C44

Suggested Citation

Haghtalab, Nika and Jackson, Matthew O. and Procaccia, Ariel, Belief Polarization in a Complex World: A Learning Theory Perspective (May 20, 2020). Available at SSRN: or

Nika Haghtalab

Cornell University ( email )

Gates Hall, Cornell University
Ithaca, NY 14853
United States

HOME PAGE: http://

Matthew O. Jackson (Contact Author)

Stanford University - Department of Economics ( email )

Landau Economics Building
579 Serra Mall
Stanford, CA 94305-6072
United States
1-650-723-3544 (Phone)


Santa Fe Institute

1399 Hyde Park Road
Santa Fe, NM 87501
United States

Ariel Procaccia

Harvard University ( email )

1875 Cambridge Street
Cambridge, MA 02138
United States

Here is the Coronavirus
related research on SSRN

Paper statistics

Abstract Views
PlumX Metrics