Bang
V. NGUYEN and Min-Yen KAN
15
Functional
Faceted Web Query Classification
3. Replicability by human subjects
nSubsampled
75 of the 100 queries
nAsked
25 human volunteers to judge
queries
nEach
query is judged by 5 evaluators.
¨Capture the average rating of all users on each facet on Likert 5-point scale
(1
sensitive, 5 insensitive)
(1
specific, 5 ambiguous)
Goals:
A. Is our classification
replicatable / understandable?
B. Are the coarse granularity
of facet values ok?