Talking to Machines

Artificially Intelligent Opinion Polling

T2M is about exploring the areas of social science research in which generative AI and LLMs can make significant contributions to what we broadly characterize as the production of research.

Talking to Machines (T2M) is a collaborative project, developing the tools that facilitate the integration of AI and behavioral social science research. PoSSUM is one of these AI tools – it polls the public by inferring the attitudes and preferences of real-life social-media users with multimodal LLMs. It is being developed by Professor Roberto Cerina in collaboration with Ray Duch, a Director of the T2M project.

PoSSUM is an AI survey research tool for well-defined data collection environments. PoSSUM requires a large corpus of data.  For the 2024 U.S. Presidential election vote estimates, PoSSUM relies on the approximately 50 million active U.S. subscribers to X (formerly Twitter).   Secondly, PoSSUM requires a large corpus of conversations, by these individuals, on “topic” that can be observed over time. Thirdly, PoSSUM adapts its LLM data collection and filtering strategies and its LLM forecasting algorithms with the assistance of a reliable stratification frame (e.g., a census of the population of interest).

PoSSUM generates profiles of public opinion and preferences that are identical to conventional polling in terms of their rich detail.  The U.S. Presidential election campaign provides a unique opportunity to test this claim. Over the course of the 2024 campaign PoSSUM will be generating bi-weekly detailed Presidential vote estimates. They will be benchmarked against conventional polling estimates and of course will face the ultimate test on November 5th.