Software Engineering White Papers
A Study on the Effects of Personalization and Task Information on Implicit Feedback Performance
Overview While Implicit Relevance Feedback (IRF) algorithms exploit users' interactions with information to customize support offered to users of search systems, it is unclear how individual and task differences impact the effectiveness of such algorithms. This paper describes a study on the effect on retrieval performance of using additional information about the user and their search tasks when developing IRF algorithms. This paper tested four algorithms that use document display time to estimate relevance, and tailored the threshold times (i.e., the time distinguishing relevance from non-relevance) to the task, the user, a combination of both, or neither. Interaction logs gathered during a longitudinal naturalistic study of online information-seeking behavior are used as stimuli for the algorithms.
| Publisher | Association for Computing Machinery | File Format | |
|---|---|---|---|
| Date Published | November 2006 | ||
| Format | White Papers | ||
| Topics | |||



