Social sensitivity, not just individual ability, is a key predictor of collective intelligence.

AI-driven analytics can now code non-verbal behaviour like silence at millisecond-level precision.

The challenge ahead is not teaching AI to notice behaviour, but to interpret it in context.

Co-authored by Ceolla Dillon O’Rourke, Aoife Ní Chíobháin, and Michael Hogan.

In education, collaborative learning is valued as a way to build the key collective intelligence skills that societies depend on: coordinating, communicating, sharing knowledge, perspective taking, and solving problems together. However, collaborative learning is not just about putting students in a group and asking them to complete a task. A group also has to manage the process of thinking together: taking turns, noticing confusion, regulating frustration, repairing misunderstandings, and deciding when to speak and when to wait. These social and embodied processes matter because collective intelligence (CI) depends not only on individual ability, but also on how well group members notice and respond to one another. Woolley et al. (2010) found that groups have higher CI when members show greater social sensitivity and share conversational turns more evenly. Successful collaboration depends partly on reading the room.

Researchers are increasingly using AI and multimodal learning analytics to make these subtle processes visible (Järvelä et al., 2020). Systems can detect speech patterns, pauses, facial expressions, and possible moments of difficulty. But noticing that something has happened is not the same as understanding what it means. A quiet moment might reflect confusion, frustration, individual concentration, or shared reflection. If social sensitivity matters for collective intelligence, can AI recognise the context behind these subtle signals, or can it only identify the pattern?

When the room goes quiet

Dang et al. (2024) explored this question by focusing on something that is easy to overlook in groupwork: the moments when nobody speaks. Their study involved 30 Finnish secondary students working in........

© Psychology Today