“Talking to Machines” is a project that aims to leverage artificial intelligence in the design and implementation of experiments.  The project leads are Sonja Vogt at HEC University of Lausanne and Ray Duch at Nuffield College University of Oxford. Our primary funding is the Swiss National Science Foundation (#100018M-215519).

We are building a team of scientists to work with us on this initiative – please check out the job postings!

We are building a team of scientists to work with us on this initiative – please check out the job postings!

Project

“Talking to Machines” is a project that aims to leverage artificial intelligence in the design and implementation of experiments. The project leads are Sonja Vogt at HEC University of Lausanne and Ray Duch at Nuffield College University of Oxford. Our primary funding is from the Swiss National Science Foundation (#100018M-215519).

An important challenge facing policy makers is the effective communication of policy-related information to the average citizen. Our focus is on the information content of video communications. People differ in many ways that are relevant when it comes to behavioral responses to the information content of videos. Any intervention – nudges, edutainment, information campaigns, or legislative changes – has heterogeneous effects among the targeted population. The Talking to Machines project uses recent methodological advances to create a platform for designing experiments with information treatment arms that consist of video narratives. How do we know what information should be incorporated into a particular treatment and how should the information be framed and delivered? Moreover, how can we address heterogeneous attitudes and needs when developing communication campaigns for diverse societies? In this project, we tackle both challenges, namely optimal design of information treatment arms that are sensitive to heterogeneous treatment effects.

Our goal is to incorporate intelligent technologies in the design of policies informing average citizens about critical behaviors related to health, saving, or education. We combine narrative information with intelligent technologies to develop effective video interventions for heterogeneous populations. There have been significant advances in computational social science that provide the tools for optimizing the design of digital content and the development of information interventions. Important elements of the project include automating the conversations with subjects who participate in these experiments; programming ChatBots to facilitate these conversations; generating large corpuses of text and voice data; LLM; machine learning data analytics; and machine-enhanced design of video treatments.

We are committed to evidence-based policies and engage with national, and international governmental agencies to evaluate the effectiveness of current policies, as well as design new programs and tools with the potential to ultimately affect the lives of millions of individuals. We are an international collaboration with a talented global team of faculty, staff, postdocs, and graduate and undergraduate students. The project is a unique combination of both academic and industry researchers working in very diverse institutional contexts throughout the world. Research results from these studies have been published widely in leading social science peer-reviewed publications.

Team

Ray Duch

Project Lead

Sonja Vogt

Project Lead

Piotr Kotlarz

Data Scientist

Melanie Sawers

Administration Manager

We are building a team of scientists to work with us on this initiative

Sponsors

Talking to Machines © 2023. All rights reserved.
Website by Alessandro [@] doliveira.me