Wizag offers semantic analysis, attention to RSS[reference] | idouba

Wizag offers semantic analysis, attention to RSS[reference]


RSS is world changing technology, but it risks getting bogged down in information overload. The simple solution is a system like MyYahoo where a limited number of feed items are displayed and the interface is most conducive to subscribing to a small number of feeds. The power user needs a lot more, though, and the holy grail for many RSS feed reader developers is a working relevance engine.

The newest player in this field is Wizag. It’s an online feed reader that incorporates attention data and semantic analysis in regards to both your feeds and the larger community of Wizag users. It recommends topics, visualized points of intersection between topics and new feeds based on your interaction with the subscriptions you already have. The implementation is a little slow and it’s nothing pretty to look at, but the technology is interesting.

The company says it aims to release an enterprise edition later this month. Unless this is a radically different tool based on the same technology it probably doesn’t stand a chance against Attensa, but for now the personal edition of Wizag is worth a look.

Wizag is a 12 person team based in Irvine, California. It’s self funded and lead by founder Ping Liang, whose previous company TransDimension made USB technology to connect digital cameras to printers and was sold to Oxford Semiconductor in 2005. In early development, Wizag was called Diggol but has changed its name – thank goodness.

A river of news option to display individual items in order of publication across all feeds is a must have for me and Wizag is lacking that to date, but there’s more to life than chronology.

Here’s what’s cool about Wizag. The service’s semantic analysis pulls topics out of each post in the feeds you are subscribed to and lets you click to read all posts in your feeds related to the same topic. Most feed readers have a search function, but Wizag finds likely topics and lists the number of other items in subscriptions that discuss the same topic. It’s a smart automation of possible searches before they are even performed.

You can tag, comment and vote on any item in your feeds. It’s a shame that this metadata stays inside Wizag, but item ranking, or determining the order that items appear in your reader, is done through an algorithm that incorporates the click-throughs, votes, comments and subscriptions you and other users have gestured with.

Rojo offers something similar, but its relevance function appears to be based entirely on the attention data of the whole Rojo community, whereas in Wizag there’s a lot you can do with your feeds through a filter of your own past behavior alone. Wizag does more with your data but has a far less friendly interface.

Wizag also offers two means of visualization that could be useful. The Topic Cloud displays the topics gleaned from the semantic analysis with the largest number of items and maps out the links between those topics. You can click on the line drawn between two topic nodes to read stories that contain both terms.

The Trend Graph displays the fastest rising and fading topics in your feeds or all user feeds over whatever period of time you select. Though other attention engines take the time factor into consideration, it’s nice that Wizag makes that data available in visual form and breaks it up into all users or just your feeds.

With time this company may be able to nail the truly useful features here and jettison some of what’s weighing the system down. Making powerful use of attention data in an RSS reader, without taking too much control away from readers, is a huge challenge. Offering extensive analytics in a clear fashion so the user experience isn’t too unpleasant is where Wizag has missed the boat so far.

Last week I profiled TouchStone, a desktop app that does a whole lot of things right. It’s a tool for information triage, though, and only a compliment for a smart system for basic feed reading. Wizag brings a number of things to the table that deserve consideration. For now I’ll stick with NetNewsWire and hope that my own manual determination of relevance doesn’t leave me missing out on too much important news.


  • Niklas 

    Sounds like a great idea… though after first registering and the importing my feeds via OPML on first try on actual use i get first a 90sec waiting time and a BIG RED EXCLAMATION and this message: “Please click Home in the navigation bar to refresh the contents.
    Error: Feeds Contents is currently unavailable.”

    After clicking home i get “Runtime Error”…

  • Sean Ammirati 

    Very interesting RSS reader, I just requested an account.

  • Greg Linden 

    C’mon, Marshall, it’s pretty lame to talk about a new personalized news and weblog aggregator without mentioning Findory.com.

    Findory learns from the articles each reader clicks on and recommends other articles. Findory also has a personalized feed reader that recommends stories selected from your favorite feeds (import OMPL or pick the feeds on Findory).

    Findory has been around for three years. It has 100k+ unique visitors per month and 5M+ page views per month. How about giving it a little love?

  • GRex 

    Bob was pretty harsh. I think Wizag is pretty innovative. Design-wise, it’d take some time to mature, as I experienced with onelurv.

    Reading from the FAQ, I see it seeks to solve almost the same problem as onelurv. The approach can’t be more different though.

    I have doubts about how it’d fare as a personal feed reader, as Mashall has pointed out. From the looks of it, it’s strength is very much in discovery.

  • The UI needs redesign, no question, but once you look at what it offers, it is very promising. The topic cloud is awesome. It finds out in my feeds what is being talked about and lets me navigate to the topics I want to read. The topics are not just 1 or 2 words like the tags. After each post, I can pursue other posts covering the same topics by clicking on the topics. I haven’t see anyone offering these features before.

  • Avatar
    Ping Liang 

    Skeptical: a healthy dose of skepticism is always good, but jumping to conclusions without knowing the whole story is not. We are using the WizAg website to showcase some of our natural language processing, text mining, personalized discovery and ranking technologies. It is a free service and is not a business model to make money. We do not place ads next to the feeds and have no plan to do so. Watch us over the next few months and you will have a better idea where we are going.

  • Skeptical Crunchie 

    More news about a startup that appeals to 0.001% of the Internet’s population. And not to mention is competing with 100 other startups with similar services. We now have an overload of services that are looking to help you with the information overload. Go figure.

    I will give them credit though. They have a potentially viable business model: “US and International Patents Pending”. Hopefully the patent settlements and licensing will pay for the salaries of the 12 employees who do god knows what.

  • Hm. perhaps some pictures would help liven it up a bit. the color scheme is currently rather painful to look at, but I do like the overall idea. Just by clicking on one of the topics and reading the titles of the posts, you’ve got a good idea of what’s going on. also, I’d like it better, faster. And the topic discovery engine is interesting…albeit unnatractive.

  • What I find interesting is that their portal is based off of an open source solution, dotnetnuke. There value add is building custom models for DNN.

  • Ping Liang 

    Bob, it is rather rude to insult TechCrunch’s integrity without evidence. Just to make it clear, we did not pay in any way or form for the coverage! TechCrunch is doing a great service to their readers and is helping a lot of startups. One of their main objectives is to alert readers of new developments and startups in their early stages.

    In our case, the UI is ugly, which Marshall had pointed out to us when he was writing it and explicitly pointed it out in his post, but our automatic Topic Discovery Engine, which is our main feature, is solid, and we believe is the best out there.

    Our main motivation is to help users find out quickly what is happening and quickly get to what they are interested in. If you subscribe to a lot of feeds, there will be hundreds of posts per day and it will be very difficult for you to read them all. If you subscribe to tens or hundreds of feeds, you know what I am talking about. The Topic Discovery Engine discovers the topics that match a user’s attention data and sort the posts into the topics.

    For example, the topics that are discovered today include “fidel castro”, “minimum wage”, “google talk”, “british prime minister tony blair”, etc. These topics are more informative and objective than tags.

  • Bob 

    Wow…what’s up with TechCrunch covering half-baked crap like this? Are you guys being paid to write about bad startups?

  • Ebrahim 

    They really need to work on their interface. Extremely ugly, quirky and non-standard.

  • Marshall Kirkpatrick 

    Thanks Brett, that probably is worth a mention – note added.

  • Formerly known as Diggol, according to the title tag of their “about” page…

原创文章。为了维护文章的版本一致、最新、可追溯,转载请注明: 转载自idouba

本文链接地址: Wizag offers semantic analysis, attention to RSS[reference]

, ,

No comments yet.