- 21
- Sphinn It!
Topic Type: News Story (Jump to http://searchengineland.com)
Category: Searching
2 Comments
2 Comments
Save the date for:
SMX Local & Mobile - San Francisco, CA (July 24-25) See the agenda, and register now!
SMX Sao Paolo - Brazil - (Aug. 7-8)
SMX China - September 23 & 24, 2008
SMX Stockholm - September 23 & 24, 2008
SMX East - NYC - (Oct. 6-8) Registration is now open.
SMX London - November 4 & 5, 2008
Comments
Very interesting interview, especially since Nielsen is not expressing much optimism about the improvements to the search in the near future. One thing that I think is missing from their discussion, is a potential shift of the search results paradigm. I don't mean the layout of results, but rather the overall expectations of users from the search. See my Sphinn post "What Users Want From Search" about an emerging alternative (http://sphinn.com/story/318).
After reading this interview, I'm convinced that there's a serious need to add search topics to usability conferences.
1. Dr. Nielsen's description of how Amazon's item-to-item collaborative filtering works is completely wrong. See;
Collaborative recommendations using item-to-item similarity mappings
http://patft.uspto.gov/netacgi/nph-Parser?Sect1=PTO2&Sect2=HITOFF&p=1&u=%2Fnetahtml%2FPTO%2Fsearch-bool.html&r=1&f=G&l=50&co1=AND&d=PTXT&s1=6,266,649.PN.&OS=PN/6,266,649&RS=PN/6,266,649
2. The SERPS of 2003 didn't include a blended mix of videos, news, maps, product search, book results, and information from many other separate databases. They didn't include mid page query refinements based upon user behavior interaction with the search engine. They didn't show query refinements from Google Base type databases. They didn't show sitelink styled links that attempt to anticipate final destinations on a domain.
3. The relevance paradigm of search engines isn't switching from an IR information system approach to a popularity approach. Popularity approaches, with quality factors like PageRank, have been around since 1998. The movement isn't towards the "best" page based upon popularity - it's an attempt to find the right page for the person searching - so that there is no one "best" page.