Loading...
Please wait, while we are loading the content...
Similar Documents
Evaluating the accuracy of implicit feedback from clicks and query reformulations in web search (2007)
| Content Provider | CiteSeerX |
|---|---|
| Author | Joachims, Thorsten Granka, Laura Inc, Google Pan, Bing Hembrooke, Helene Radlinski, Filip Gay, Geri |
| Abstract | This article examines the reliability of implicit feedback generated from clickthrough data and query reformulations in World Wide Web (WWW) search. Analyzing the users ’ decision process using eyetracking and comparing implicit feedback against manual relevance judgments, we conclude that clicks are informative but biased. While this makes the interpretation of clicks as absolute relevance judgments difficult, we show that relative preferences derived from clicks are reasonably accurate on average. We find that such relative preferences are accurate not only between results from an individual query, but across multiple sets of results within chains of query reformulations. |
| File Format | |
| Journal | ACM Trans. Inf. Syst |
| Language | English |
| Publisher Date | 2007-01-01 |
| Access Restriction | Open |
| Subject Keyword | Implicit Feedback Query Reformulations Web Search Relative Preference World Wide Web Manual Relevance Judgment Clickthrough Data Individual Query Multiple Set User Decision Process Absolute Relevance Judgment |
| Content Type | Text |
| Resource Type | Article |
