130 likes | 356 Views
Evaluating Implicit Measures to Improve the Search Experience. SIGIR 2003 Steve Fox . Outline. Background Approach Data Analysis Value-Add Contributions Result-Level Findings Session-Level Findings. Background. Interested in implicit measures to improve user’s search experience
E N D
Evaluating Implicit Measures to Improve the Search Experience SIGIR 2003 Steve Fox
Outline • Background • Approach • Data Analysis • Value-Add Contributions • Result-Level Findings • Session-Level Findings
Background • Interested in implicit measures to improve user’s search experience • What the user wants • What satisfies them • Significant implicit measures • Needed to prove it! • Two goals: • Test association between implicit measures and user satisfaction • Understand what implicit measures were useful within this association
Approach • Architecture • Internet Explorer add-in • Client-Server • Configured for MSN Search and Google • Deployment • Internal MS employees (n = 146) – work environment • Implicit measures and explicit feedback • SQL Server back-end
Data Analysis • Bayesian modeling at result and session level • Trained on 80% and tested on 20% • Three levels of SAT – VSAT, PSAT & DSAT • Implicit measures:
Result-Level Findings • Dwell time, clickthrough and exit type strongest predictors of SAT • Printing and Adding to Favorites highly predictive of SAT when present • Combined measures predict SAT better than clickthrough
Result Level Findings, cont’d Only clickthrough Combined measures Combined measures with confidence of > 0.5 (80-20 train/test split)
Session-Level Findings • Four findings: • Strong predictor of session-level SAT was result-level SAT • Dwell time strong predictor of SAT • Combination of (slightly different) implicit measures could predict SAT better than clickthrough • Some gene sequences predict SAT (preliminary and descriptive)
Session Level Findings, cont’d • Common patterns in gene analysis, e.g. SqLrZ • Session starts (S) • Submit a query (q) • Result list returned (L) • Click a result (r) • Exit on result (Z)
Value-Add Contributions • Deployed in the work setting • Collected data in context of web search • Rich user behavior data stream • Annotated data stream with explicit judgment • Used new methodology to analyze the data • ‘Gene analysis’ to analyze usage patterns • Mapped usage patterns to SAT