First ACM International Conference on Web Search and Data Mining - WSDM 2008

Entropy of Search Logs: How Hard is Search? With Personalization? With Backoff?

author: Qiaozhu Mei, Department of Electrical Engineering and Computer Science, University of Michigan
published: Feb. 25, 2008, recorded: February 2008, views: 725

Slides

Slides
0:00	Entropy of Search Logs
0:34	How Big is the Web?
1:53	Millions (Not Billions)
2:13	Population Bound
3:26	It Will Take Decades to Reach Population Bound
3:55	Equilibrium: Supply = Demand
4:30	Demand Side Accounting
5:08	How Big is the Web?
6:04	Chomskian Argument: Web is Infinite
6:41	How Bigis the Web? 5B? 20B? More? Less?
8:03	Entropy (H)
8:38	How Hard Is Search?
9:40	Difficulty of Queries
10:14	How Hard are Query Suggestions?
10:44	Personalization with Backoff
11:52	Backoff
12:20	Backing Off by IP
13:32	Personalization with Backoff -> Market Segmentation (1)
14:16	Personalization with Backoff -> Market Segmentation (2)
14:58	Business Days v. Weekends: More Clicks and Easier Queries
15:27	Day v.s. Night: More Queries, More Diversified Queries
15:45	Harder Queries at TV Time
16:08	Conclusions: Millions (not Billions)
16:59	Conclusions: Personalization with Backoff
17:42	Thanks!
25:15	- Questions
25:48	- Questions

Report a problem or upload files

If you have found a problem with this lecture or would like to send us extra material, articles, exercises, etc., please use our ticket system to describe your request and upload the data.
Enter your e-mail into the 'Cc' field, and we will keep you updated with your request's status.

Lecture popularity: You need to login to cast your vote.