Microsoft researchers described query refinement, result clicks, and dwell times as behavioral signals used to estimate search satisfaction.

Cited by documentation

Sources

• Personalized Models of Search Satisfaction (CIKM 2013)

  Microsoft Research (ACM CIKM 2013) · primary source · retrieved 2026-08-21

  “estimate satisfaction from behavioral signals such as query refinement, result clicks, and dwell times” — Abstract

  “abandonment, dwell time, and query refinement” — Section 1/roadmap paragraph

• Modeling Dwell Time to Predict Click-level Satisfaction (WSDM 2014)

  Microsoft Research (ACM WSDM 2014) · primary source · retrieved 2026-08-21

  “Clicks on search results are the most widely used behavioral signals for predicting search satisfaction” — Abstract/introduction

• Beyond Clicks: Query Reformulation as a Predictor of Search Satisfaction (CIKM 2013)

  Microsoft Research (ACM CIKM 2013) · primary source · retrieved 2026-08-21

  “implicit behavior is a useful data source, with clicks being the best-known implicit signal” — Abstract

• Personalized Models of Search Satisfaction

  Microsoft Research · primary source · retrieved 2026-08-21

  “behavioral signals such as query refinement, result clicks, and dwell times” — HTML line 10

• Do affective cues validate behavioural metrics for search?

  Microsoft Research · primary source · retrieved 2026-08-21

  “query reformulation or clicks, are commonly used to evaluate a running search engine” — HTML line 16

  “short dwell time are associated with a decrease in smiles” — HTML line 18