Related Experiment Video
Updated: Sep 10, 2025

Assessing the Multiple Dimensions of Engagement to Characterize Learning: A Neurophysiological Perspective
Published on: July 1, 2015
Ranking by engagement and non-engagement signals: Learnings from industry
Tom Cunningham1, Sana Pandey2, Leif Sigerson3
1OpenAI Inc, San Francisco, California, USA.
Abstract:
Many online media platforms primarily rank items by predicted user engagement, yet we see substantial potential in incorporating non-engagement signals-such as user surveys or quality metrics-to benefit both platforms and society. Drawing on a daylong workshop with experts from various industry platforms and academia, we developed a series of propositions related to non-engagement signals that gained broad consensus. These propositions examine the relationships between engagement, non-engagement signals, and key metrics like user retention. We document each proposition with publicly available evidence, including quantitative results where possible. Given the cost and time associated with industry experimentation on non-engagement signals, we believe sharing these insights will be valuable for advancing common knowledge.
Related Concept Videos
Energy and Power Signals
Amplifying Signals via Enzymatic Cascade
Interactions Between Signaling Pathways
Convergence and divergence, and cross-talk between signaling pathways
Two distinct signaling pathways can converge on a single functional unit, which may either be a single protein or a complex of proteins. The response is either functionally distinct or synergistic between the two pathways but different from the response...
Ranks
Amplifying Signals via Second Messengers
Classification of Signals
A continuous-time signal holds a value at every instant in time, representing information seamlessly. In contrast, a discrete-time signal holds values only at specific moments, often denoted as x(n), where...

