I’ll be presenting later today at the Search Engine Strategies at San Jose, and the session I’m talking at involves Search Algorithms and the patents and whitepapers that describe them.
My presentation will focus upon Google as a recommendation system. With some fortunate timing, Google had a new patent granted today, which describes how Google could be used as a recommendation system when it comes to ecommerce.
Interface and system for providing persistent contextual relevance for commerce activities in a networked environment
Invented by Donald R. Turnbull and Hinrich Schuetze
Assigned to Google
United States Patent 7,089,237
Granted August 8, 2006
Filed: January 26, 2001
Continue reading Google as a Recommendation System
One of the things that I don’t get to do on the east coast of the United States is to go to some of the more spontaneous events happening in the world of the Internet and web development.
But, after a red-eye flight to the west coast ending yesterday at the San Francisco Airport around noon, I find myself with the luxury of signing up for WordCamp 2006. This is a day long conference for users and developers of wordpress software, which happens tomorrow, Saturday – August 5th, 2006, from 9 AM – 6 PM, with a 8:30 PM after-party. The location is the Swedish American Hall, San Francisco CA. The conference is free, and it could be fun to have the ability to provide some input into the future growth of wordpress. There’s a big list of suggested sessions, and it should be fun to discuss many of those topics with people who are passionate on the subect.
I’ll be in San Jose next week at the Search Engine Strategies Conference, speaking on Tuesday afternoon alongside Rand Fishkin of Seomoz and Jon Glick of become.com, in a presentation on Search Algorithm Research.
My part of the presentation will be focusing upon how the analysis of queries from users is playing a stronger role in what the search engines serve, how they collect information from users, and how they could expand their personalization efforts by looking at information outside of the interaction they have with their users.
Continue reading Attending Wordcamp 2006 and SES San Jose 2006
I received an email on Sunday night from Dr. Abdur Chowdhury of AOL, who asked me if I would take a look at a new site that the folks at AOL have put together. I haven’t had much of a chance to look at the site, but what I’ve seen so far, I like very much.
I’m hoping that I can get some comments here, about these new wiki pages from AOL, if you have some time. The site is still in alpha, but they are welcoming comments there, too.
‘http://research.aol.com/pmwiki/” (Note: this research was removed after controversy over the release of data contained there.)
There’s some great information there, like 500K user queries, collected over a three month span. There’s also a nice set of publications, including more than a couple co-authored by Dr. Chowdhury.
Continue reading AOL Open Research Information Retrieval Wiki
One of the most common activities on the web is searching for answers to questions, and search engines are one way to find some answers. But they aren’t the only means available on the web and people have been turning to places like forums, through usenet, and in many different sites that provide people the chance to interact.
Microsoft has a new patent application for a Game-powered search engine (US Patent Application 20060167874) that looks at some of those means as the groundwork for this invention of theirs.
The listed inventors are Luis A. von Ahn Arellano, Eric D. Brill, John C. Platt, and Josh Benaloh, and it was filed on January 24, 2005 and published July 27, 2006. Here’s the abstract:
The subject invention provides a unique system and method that facilitates an interactive game-powered search engine that serve the purposes of both users who may be looking for information as well as game participants who may desire to earn some reward or level of enjoyment by playing the game. More specifically, the system and method provides feedback to a user based on the user’s input string or a string derived therefrom. The feedback can be a response or answer to the user’s input in the form of text, an image, audio or sound, video, and/or a URL that is provided by one or more game participants when there is some degree of consistency or agreement between the responses or when individual players have demonstrated good reliability in their responses.
Continue reading Playing Games and Answering Questions
A local search engine works by attempting to return relevant web pages associated with a specific geographical region or location. When the search engines index web pages, it can be helpful to attempt to automatically associate thoses pages, or sections of them with specific places or regions.
Ideally, for example, a web page about a restaurant in New York City should be associated with New York City. This connection can be easier to create if there is clearly a postal address or other geographical information on the page associated with that location and restuarant. But sometimes, a page will only contain a partial address or information that makes it difficult to to draw that connection between page and place.
Another issue that comes up in local search is which geographical region should the search engine show results from when there may be more than one location or region with the same name, or a similar name. For instance, If I want to order a pizza from one of the local pizzerias, I might search for Pizza Newark, but I probably won’t be happy with the Google local results which show Newark, New Jersey, pizza places, instead of Newark, Delaware.
Yes, I can add a zip code, or state name, and that will solve the problem. But I want to know why the local search chooses New Jersey. Is Newark New Jersey, the most important Newark in the world, or is there some other reason?
Continue reading Which Newark is the Dominant Newark? Classification of Ambiguous Geographical References in Local Search
When I search for Pizza in New York in Google Local, I’m told that there are about 79,400 results. The top result I see is Lombardi’s Pizza, which is “0.8 mi NE” of the green arrow on the map that points to New York.
Exactly what is that green arrow pointing to, and why does Lombardi’s Pizza show up number one?
To rephrase that question, how does a site to become the “authority” for a region, for a business type, rather than an authority for a specific location and business name?
In Authority Documents for Google’s Local Search, I wrote about a patent application that described how a specific site would show up first when searching for a specific business name and location. The author of that patent filing, Daniel Egnor, was the named inventor on a number of others on local search that came out the same week. This post is about one of those other ones, which is the only one I can recall from Google that talks about identifying specific regions, and tying them to queries about business types:
Indexing documents according to geographical relevance
US Patent Application 20060149774
Continue reading Pizza at the Center of New York: Relevancy, Google Local, and Local Results in Organic Searches
Living in a college town, it’s not uncommon to see bulletin boards with activities, opportunities, and advertisements listed all over them. There’s a certain artistic aspect to them when taken in from a short distance.
One of my favorite music stores has a board like that on the side of their building. I was reminded of that when a friend sent me a link to a page that he’s building called The Flyer Wall. There’s an aspect to it of the million dollar homepage, but one main difference is that the designer behind the page is an excellent graphic artist, and he’s creating the images behind the flyers’ posted on the wall. It’s still in its infancy, but I like what he’s done.
Was the million dollar homepage a one time phenomenon? Will people be attracted to a site like this, designed by a skilled graphic artist? I’m not sure, but we will probably see more like it in the months to come.
Imagine taking the concept off the web, and onto a building – ‘Million Dollar Homepage’ Concept Hits Outdoor Market
Some very good news from Reuters (via John Blossoms’s Content Blogger), Google is testing more accessible Web search for the visually impaired.
At Google Labs, you can now find Google’s Accessible Web Search for the Visually Challenged . It doesn’t look that different from the regular Google Interface, but the difference appears to happen behind the scenes. According the Accessible Search FAQ, it goes beyond finding the most relevant results by finding the most accessible pages from the normal web search result set.
I tried a few searches, and they confirmed that rankings do change, and sometimes significantly, for those searches. I’m seeing sites that were constructed with accessibility as a major goal move up considerably in rankings.
The FAQ tells us that it looks at HTML markup, and
Continue reading Cheers for Google’s New Accessible Search