Lisa Feldman Barrett co-authors opinion paper: ML can't settle emotion science's century-old debate
burny_tech · x · 2026-11-04
A Trends in Cognitive Sciences opinion paper by Kieran McVeigh, Andrew Smart and Lisa Feldman Barrett et al. examines what machine learning can discover about the nature of emotion.
- The field increasingly leans on ML hoping for objective discoveries to resolve century-long debates between topological and constructionist traditions.
- The authors show confirmation bias arises when theory-based hypotheses are evaluated via theory-laden sampling, model specification, and feature choices.
- Because each tradition manifests its theoretical differences in its ML methods, ML cannot settle those differences.
- They argue emotion research is never free of human experience and beliefs, but a theory-aware research strategy can reduce bias and yield more justified knowledge.
More from Research
- NRGPT paper reimagines GPT inference as gradient descent on an explicit energy landscape — burkov · 2026-11-04
- Fireworks event slides show sliding-window bit-sharing quantization trick — sophiamyang · 2026-11-04
- UCLA Study Seeks Users of 'Griefbots' to Interview on AI and Mourning ($30 Gift Card) — Interesting-Cat-7838 · 2026-11-04
- Tiny LoRA adapter beats DNA model Carbon-X on RareBench, exposing generalization limits — danielmckinn0n · 2026-11-04
- QuickProof: formal verification for C with specs written as plain C tests — thomasahle · 2026-11-04
- RSNA 2026 Deep Learning Lab to teach medical imaging VLM dataset building from scratch — PRouzrokh · 2026-11-04