Evaluating sources of implicit feedback for web search Public Deposited
Downloadable ContentDownload PDF
- Last Modified
- March 21, 2019
- Affiliation: School of Information and Library Science
- This dissertation investigated several important issues in using implicit feedback techniques to assist searchers with difficulties in formulating effective search strategies. The study focused on examining the relationship between types of behavioral evidence that can be captured from Web searches and searchers’ interests. Web search cases which involved underspecification of information needs at the beginning and modification of search strategies during the search process were collected and reviewed by human analysts (reference librarians) who tried to infer searchers’ interests from behavioral traces. Analysts’ rationales for making the inferences were elicited and analyzed with the focus on understanding what evidence was used to support the inferences and how it was used. The analysis revealed the complexities and nuances in using behavioral evidence for implicit feedback and led to the proposal of an implicit feedback model for Web search that bridged previous studies on behavioral evidence and implicit feedback measures. A new level of analysis termed an analytical lens emerged from the data and provides a road map for future research on this topic. The study also put forward design recommendations for implicit feedback systems based on the signals that analysts identified and the rules that they used in making inferences.
- Date of publication
- May 2008
- Resource type
- Rights statement
- In Copyright
- Marchionini, Gary
- Open access
This work has no parents.
|Evaluating sources of implicit feedback for web search||2019-04-09||Public||