Can artificial intelligence tell whether a team is on the same page or talking past each other—even when its members are spread across two continents?
At the CHI 2026 in Barcelona, Christopher Micek, Lasse Warnke, Lourenço Abrunhosa Rodrigues, Felix Putze (University of Bremen / Lifespan AI), and Erin Solovey (WPI) presented a new multimodal dataset that enables the systematic measurement of cognitive team states in distributed environments. The data was collected from teams collaborating simultaneously in Europe and North America using synchronized EEG measurements, audio transcripts, screen recordings, and behavioral annotations. The goal is to develop adaptive interfaces that respond in real time to the team’s mental state.
In an increasingly distributed work environment, it is crucial to develop systems that not only automate tasks but also support people in efficient teamwork. EEG-based systems can measure concentration, cognitive load, and divided attention. Factors that are critical to the quality of collaborative work. The dataset presented here is one of the first to enable these measurements in naturalistic, geographically distributed settings.