(October 27, 2015) Resumen:
Universidad Carlos III de Madrid is investigating how to build a system that recreates
human behavior. This technology could be applied to anticipate behavior in
socioeconomic crises, create more human-like robots or develop avatars of
artificial intelligence which are almost indistinguishable from those that
represent people.
The research project, called IBSEN (Bridging the gap: from
individual behaviour to the socio-tEchnical Man), is part of a call for “novel
ideas for radically new technologies” (FET-Open) by the European Union’s
Horizon 2020 program. The UC3M coordinates the project and scientists in Spain
from the Universitat de València and the Universidad de Zaragoza also
participate, as well as other British, Finnish and Dutch researchers.
“We are going to lay the foundations to start a new way of
doing social science for the problems that arise in a society that is very
technologically connected,” explains the head of the project, Anxo Sánchez,
from the UC3M Interdisciplinary Mathematics group.
The goal of the project is to understand the behavior of
people on an individual level, especially when they are connected by new
technologies like mobile telephones or social networks. To this end, this group
of scientists is preparing experiments which will present certain problems of
cooperation, social problems and economic games simultaneously to thousands of
people to try to decipher the hidden patterns behind their decisions.
With this information, researchers will afterwards be able
to create a simulator of human behavior, a technology that will provide a basis
for socioeconomic simulations that will radically change many fields, from
robotics to economics, with technological and social impacts like the
formulation of policies and decisions about pressing social issues.
“The greatest difficulty is to design a new experimental
protocol that allows us to ensure that all the participants in the experiment
are available at the same time and really interact, because you are not
observing them in a laboratory,” say the researchers, who are used to doing
this kind of experiment in laboratories where they work with groups of 50 to 60
people, when in this case there are more than 1,000 participants.
The challenge posed by this project, once the experiments
are done, is to obtain a repertoire of human conduct that makes it possible to
simulate the behavior of a person and apply it to a robot or recreate what
large groups of people will do in certain circumstances. “On an individual
level, it could be used to improve the realism of characters in video games and
humanize the avatars one interacts with in the help section of web pages,” said
Sánchez. “And with regard to the simulation of collective behavior, it would
allow us to try to understand the evolution of the economy and the appearance
of social disorders.”