Topic relevance

1. A computer implemented method of determining the relevance of a destination page to a topic comprising:

determining a plurality of paths that include arrivals at the destination page, at least in part by modeling a random surfer who visits links in accordance with a mathematical model, the random surfer having one of a plurality of associated states, the states indicating whether the surfer has visited at least one seed page included in a seed set that includes a plurality of seed pages;

determining the relevance of the surfer as either being relevant or irrelevant based at least in part on the surfer's behaviors corresponding to the plurality of paths; and

determining the relevance of the destination page to the topic, at least in part by determining a ratio of (1) a measure of paths included in the plurality that include an arrival at a distinguished page preceding an arrival at the destination page and (2) a measure of the plurality of paths and (3) the relevance of the surfers corresponding to the plurality of paths.

2. The method of claim 1 wherein determining a proportion of the paths includes counting all arrivals at the destination page and counting all arrivals at the page preceded by arrivals at the distinguished page.

3. The method of claim 1 wherein the proportion is weighted.

4. The method of claim 1 wherein determining the relevance includes determining a backward relevance.

5. The method of claim 1 wherein determining the relevance includes determining a non-teleport relevance.

6. A system for determining the relevance of a destination page to a topic comprising:

a processor, configured to:

determine a plurality of paths that include arrivals at the destination page, at least in part by modeling a random surfer who visits links in accordance with a mathematical model, the random surfer having one of a plurality of associated states, the states indicating whether the surfer has visited at least one seed page included in a seed set that includes a plurality of seed pages;

determine the relevance of surfer as either being relevant or irrelevant based at least in part on the surfer's behaviors corresponding to the plurality of paths;

determine the relevance of the destination page to the topic, at least in part by determining a ratio of (1) a measure of paths included in the plurality that include an arrival at a distinguished page preceding an arrival at the destination page and (2) a measure of the plurality of paths and (3) the relevance of the surfers corresponding to the plurality of paths; and

a memory, coupled with the processor, wherein the memory is configured to provide the processor with instructions.

7. The system of claim 6 wherein determining a proportion of the paths includes counting all arrivals at the destination page and counting all arrivals at the page preceded by arrivals at the distinguished page.

8. The system of claim 6 wherein the proportion is weighted.

9. The system of claim 6 wherein determining the relevance includes determining a backward relevance.

10. The system of claim 6 wherein determining the relevance includes determining a non-teleport relevance.

11. A computer program product for determining the relevance of a destination page to a topic, the computer program product being embodied in a computer readable storage medium and comprising computer instructions for:

determining a plurality of paths that include arrivals at the destination page, at least in part by modeling a random surfer who visits links in accordance with a mathematical model, the random surfer having one of a plurality of associated states, the states indicating whether the surfer has visited at least one seed page included in a seed set that includes a plurality of seed pages;

determining the relevance of surfer as either being relevant or irrelevant based at least in part on the surfer's behaviors corresponding to the plurality of paths;

and

determining the relevance of the destination page to the topic, at least in part by determining a ratio of (1) a measure of paths included in the plurality that include an arrival at a distinguished page preceding an arrival at the destination page and (2) a measure of the plurality of paths and (3) the relevance of the surfers corresponding to the plurality of paths.

12. A computer program product as recited in claim 11 , wherein determining a proportion of the paths includes counting all arrivals at the destination page and counting all arrivals at the page preceded by arrivals at the distinguished page.

13. A computer program product as recited in claim 11 , wherein determining the relevance includes determining a backward relevance.

14. A computer program product as recited in claim 11 , wherein determining the relevance includes determining a non-teleport relevance.

15. A computer program product as recited in claim 11 , wherein the proportion is weighted.