Imagine that you are scrolling through a page, and see a section of the page highlighted. The text in that area matches an interest profile that you recently created, or it’s along with the same topics that you’ve been searching through. Or it is somehow conceptually related to whatever you searched for that may have brought you to this page.
A patent application from the Palo Alto Research Center describes how something like this might work. Instead of highlighting only keywords, the following suggests ways to highlight sentences and sections of web pages that related in some conceptual manner to something that you may be searching for.
Method for automatically performing conceptual highlighting in electronic text
The inventors named in the patent are:
Stuart K. Card
Ed H. Chi
Lichan Hong
Here’s the abstract:
A method is disclosed for automatically performing conceptual highlighting of electronic text. User’s interests can be explicitly determined via keywords that the user specifies, and/or are implicitly constructed from user browsing and reading activity. User interests may be expressed as an interest profile. Conceptual keywords related to user interests are selected by combining spreading activation and word co-occurrence, by latent semantic analysis, or other methods. The invention automatically highlights sentences and other information that contains conceptual keywords related to user interests. Highlights can be activated when the user directly performs a keyword search or index search, or the invention can generate information reflecting user interests, apply it to the text, and generate and display highlights. An algorithm is disclosed for computing a conceptual keyword vector through an iterative spreading activation process also employing word co-occurrence. A conceptual index of the text may be created and then combined with conceptual highlighting.
In this process, use’s interests are determined through:
- Keywords that the user specifies,
- User browsing and reading activity. and/or ;
- User interests in an interest profile.
If you would like to avoid the legalese, a paper that looks at the highlighting process involved is ScentHighlights: Highlighting Conceptually-Related Sentences during Reading (pdf).
While it doesn’t discuss the user interest aspect of the process involved in much detail, it does take a look at how this process can help someone find something of interest in a long document.
I’d love to see something like this incorporated into a search engine.
It is amazing how detailed the search engines can get with analyzing and showing data. I wonder how far we are from totally relying on the “I am feeling lucky” button.
I agree with you, Yuri. Some amazing stuff, indeed. I can see that “I am feeling lucky” button bringing different results for different people sometime sooner rather than later.
Some of the stuff I think about when I see something like this is:
1. Will it happen, and when will we be able to use it?
2. Should it be something that we think about as we build pages? How might be take something like this into consideration?
Hmmm.. sure sounds fancy, but is it really more than a better way to highlight matches such as Google does in the cache pages? Sure you can dream of extending that, but for a practical purpose? Ithink that will definitely be the “hard part”.
Hi John,
After all of the posts I’ve read of yours at threadwatch, I was hoping that you had a blog of your own somewhere. Thanks for a link to it.
It’s hard not to look at something like this with two different hats on. One hat as a searcher who might be interested in finding information, and another as someone who studies search engines, and tries to understand how they do what they do.
Patents aren’t always revolutionary. More often, they are a way of taking something that exists, and attempting to add to it something else that other people aren’t doing. This seems to add at least two different things to the highlighting that a Google already does:
1. Some way to find information related to keywords, in addition to those keywords, or;
2. information that may match a user profile or that may be related to prior search history.
These aren’t giant steps, but they also aren’t things that people are doing now. And while big changes do spring up sometimes, often they come about from smaller changes over time.
I’m not convinced that this is the best way to collect user interests though. Maybe an Interestmap (pdf), combined with that profile and search history is the next big step.