Social Categorization and Cooperation between Humans and Computers

Celso de MeloUSC Marshall School of Business
Peter CarnevaleUSC Marshall School of Business
Jonathan GratchUSC Institute for Creative Technologies


Computers increasingly perform a variety of important tasks and services that influence individuals and organizations, yet few studies tell us about how humans interact with computers and other non-human decision-makers. In four experiments, we asked people to engage in cooperation tasks with computers and with humans. Experiment 1 found that people gave more money to a human than a computer. We argue this effect reflects a basic bias in favor of humans, which are perceived to be the in-group, when compared to computers, which are perceived to be the out-group. In Experiment 2, we varied computer and human ethnicity to be the same or different as the participant; results indicated that ethnicity had a parallel but additive effect that was independent to the effect of the human social category. The data of Experiment 3 indicate that it is also possible to promote group membership with computers by creating structural interdependence based on shared incentives. Finally, we demonstrate in Experiment 4 that our framework based on social categorization theory can predict situations where people will cooperate more with computers than with humans. We discuss implications for understanding people’s decision making with human and non-human others.


Social Categorization and Cooperation between Humans and Computers (144 KB)

Back to Table of Contents