I’ve created a service on GistWeb that creates summaries of top news stories every 2 hours in the following categories:
1. World News
2. U.S. News
3. Business News
4. Sci/Tech News
5. Sports
6. Entertainment
7. Health
These are summaries of up to 30 articles about each news item, which help you get a much more well-rounded idea of what’s going on […]

Okay guys.  Lots of you begged me to get GistWeb summaries working again.  It took some hacking, but it’s up and running again.
The gotcha is that you have to use Internet Explorer, and you have to set gistweb.com as a “Trusted Site” in IE.  To do this, go to the Tools -> Internet Options menu.  […]

Just an FYI everybody.  The GistWeb web summaries are not back up and running.  There was a problem with fetching search results that has been resolved.  Hopefully it will not occur again.
I apologize for the long delay in the fix, but with my newborn son here and GistWeb being a free resource, I had to […]

GistLite
GistLite is the original algorithm used by GistWeb to create the multi-document summaries.  It works well on a large variety of keywords.
Choose GistLite as the algorithm for your summary if your keywords are not likely to return a lot of textual content (e.g. highly commercial keywords).  GistLite will do a better job with more text […]

I was looking at the results from GistWeb’s new search summaries today, and I noticed that the first paragraph was very often spot on target, and that the rest of the pargraphs, while generally very good, didn’t meet up with the same level of quality as the introductory paragraph.
‘Well,’ I said, ‘I’ll just apply the […]

Okay guys, this is BIG news.  I’ve added a multi-document summarizer to GistWeb.  It will take the top 10, 20 or 30 pages resulting from a search query and extract only the most important information from each page and display it in a remarkably readable summary.
Here’s the link:
http://gistweb.com/web.php
It will create summaries from Google, Google News […]

Dr. Wellman said that the virus was “very dangerous to the preservation of the human race.  It has the potential to wipe out the world!”
Before this update, the above sentence would get split at “human race”, with GistWeb believing that to be the end of the sentence.  This new update allows the algorithm to recognize […]

Prior to now, GistWeb analyzed the text of an entire page to decide how much it should cut out.  While this obviously worked quite well, I’ve made it even better.
Now GistWeb looks at each paragraph in the text, and makes a decision on a paragraph-by-paragraph basis.  This has resulted in, I feel, a significant improvement […]

I noticed that when gisting blogs, GistWeb was lumping the comments in with the rest of the text.  This could be a bad thing, because a comment might be written in such a way that — when viewed in GistWeb — it appears to actually be part of the article.  That would be misleading, so […]

Okay guys, your comments on my first post got me focused on a way to improve the text-parsing algorithm that finds the “meat” on any page.
A number of folks commented that, for blogs they run through GistWeb, they were seeing parts of the navigation, footer, etc. come out in the content.
That got me to sit […]