When you're reading any item from a particular feed, you'll notice thumbs up/thumbs down buttons at the top for voting and a button that keeps track of how many votes a particular post has received. There's also an option to email the article to a friend or bookmark it for yourself.

Viewing a Post on FeedzZ

However, what's really interesting are the tags at the bottom of the post. These tags aren't generated by people, but by the underlying semantic technologies. For example, our recent post "Watch Out Silicon Valley: Here Comes NYC" was tagged: new york michael bloomberg internet week web-oriented technologies seed-stage technology fund. There's also a "related entries" link which displays a list of posts with at least one of the same tags. In this example, thanks to the tag "New York," there were several unrelated entries listed here, but there was also a link to an article about the NYC Seed Fund. So in this case, the more accurate results came from just viewing the "internet week" tag.

In addition to the tags on each post, every page of FeedzZ has an automatically generated, semantically created tag cloud on the left which you can use to see all the posts about a particular subject (Example: Bill Gates).

Issues With FeedzZ

Of course, these related entries and tags could become infinitely more useful if you were to upload your own OPML file. Unfortunately, for true feed junkies that's probably something that will have to wait, since FeedzZ currently imposes a limit on OPML file sizes, restricting them 100 KB or less. (At 142 KB for my subscription list, I was out of luck).

FeedzZ is certainly an interesting experiment in semantics, but that being said, the site still needs a lot more finesse to really be successful. The OPML restriction is only one of the issues. Even if you manage to get your OPML uploaded, it's difficult to determine how to proceed with the data you've imported. You have to find your way into your profile section (no link is provided) and then you have to create a folder structure and classify your feeds. Shouldn't a semantic system know where the feeds belong? When I tried this, I couldn't even classify my feeds manually. Although I clicked the "Classify" button, there was never a feed in the drop-down list to select (see below), so I couldn't proceed. It's as if that piece of the web site was not even built yet.

Attempting to Classify a Feed

These types of issues are major problems in terms of usability, so it's hard to truly recommend the site at this time. However, if these problems were resolved, FeedzZ could then have a shot at being a useful online feed aggregator or even a great research tool for finding related news items on the topics that interest you. It's great that FeedzZ has managed to get the semantic RSS technologies working, but now they need to turn their attention to the user experience and UI design so we all can appreciate their efforts.

Standards?

No. Inform crunches straight text and outputs HTML. I asked whether they publish content with any standards based semantic markup and they said that actual publishing is up to publishers. That's a shame, I don't see any reason why Inform wouldn't participate in the larger semantic web to make its publishers' content more discoverable. Perhaps when you've got 100 live clients and now $15m in the bank, it feels like there's no reason to open up and play nice with a movement of dreamers having trouble getting other apps out of academia.

Different Approaches

While many publishers have been criticized for linking only to their own internal pages for reference (including many leading blogs) it's good to see that Inform at least provides the option of including outside links. That is, after all, one of the most important characteristics of the web - links from one site to another.

Inform indexes blogs, audio and video as well at standard web pages. It's a smart idea and similar to a number of related companies you may be more familiar with. Our own Alex Iskold runs AdaptiveBlue, a semantic company that offers related links tied to links already added by publishers and a semantic browser plug-in. SystemOne is an elegant system that offers related content automatically during the writing process. Lijit is a custom search engine of sorts, allowing you and your readers to manually search through a confined set of content.

The key way the above services probably differ is the degree of automation that they offer. Inform is highly automated, once a publisher sets up general rules for brining in related content. A publisher might say, for example, to insert a link to their own content on any terms they have more than 20 articles about from the past week, or that their affiliate network can provide content for with a certain minimum percentage of relevance.

There's some heavy math and linguistics going on at Inform and it's a good example of how proprietary technology is headed for the bank while open standards based approaches dawdle. In theory openness and standards should be clear winners in terms of ultimate value delivered to any company, someday. In the meantime, publishers can deploy Inform's semantic technology now.