Feeds 2.0

After having spent endless hours working towards making the best RSS aggregator out there, we decided its time for a (well deserved!) break

After all, it’s the middle of the summer and we are located in Greece for Christ’s sake! So what else could be better than an escape to a beautiful Greek island for a few days, so that we can have a break from servers, administrative tasks, coding, coding (and coding), answering e-mails, taking requests, giving support, making financing round discussions, blogging, … you name it!

Of course the service will be up and running during all this time for our beta users and it will be also accepting new user registrations.

But most importantly, when we get back….. we have a big surprise for you!

See you all in mid-August.

Have a nice summer!

We have good news!

Earlier today our powerful new super-server was installed at the Data Center, and we are currently migrating our database to it. Yes, you’ve guessed it, this means that more account activations will be given out very soon, so please keep a close eye on your mailboxes

The Service will be unavailable probably for the whole day today (July 24th), and we expect at least 2 days of temporal unavailability, since we have to run a lot of tests before we reach an acceptable level of stability.

We are sorry for the inconvenience but we hope that you realize that this is a necessary step that will bring us closer to a public launch

Thanks

This past week Nicholas, our CEO, was interviewed by Doug Sherrets, the co-blogger of Minority Rapport. Minority Rapport interviews Web 2.0 companies and, according to Doug, the blog’s had 13,000 readers. The interview has been very interesting since the questions were very clearly thought of and up to the point. Here they are:

1. What is Feeds 2?
2. What makes you unique to other personalization engines, such as Findory?
3. What do you consider to be the best part of Feeds 2?
4. How does the personalization engine work?
5. What is the extent of your intellectual property? What do you holds patents for?
6. Who do you consider to be your closest competitors?
7. What do you think of Microsoft’s introduction of RSS to IE 7.0? How does that fit into the picture?
8. There has been lot of criticism about “web 2.0″ services not being designed for mainstream usage. How did you think about that in crafting Feeds 2?
9. How are you or do you plan to promote Feeds 2?
10. How do you see Feeds 2 working as an enterprise solution?
11. Do you have venture financing?
12. How much funding are you seeking to meet your business needs?
13. What is the business model for Feeds 2?
14. With enterprises, what kind of pricing model would you use?
15. It seems Feeds 2 is addressing information overload. Do you have some more thoughts on how you think about solving information overload, and perhaps you can speak to feedback from your users with respect to the effectiveness of personalization?

You can read Doug’s post (and of course hear the podcast) here or here.

In his blog Jon Silk talks about five tools that help him keep alive in the blogosphere. He then started a meme which is currently rapidly propagating across the blogosphere by challenging famous bloggers like Robert Scoble, Hugh McLeod, Guy Kawasaki, Dennis Howlett and David Tebbutt to respond first by naming their top five tools.

Dennis Howlett (disclosure: whom we met at the Innovate!Europe 2006 event at Zaragoza in May and has been one of our first beta users) notices the lack of personalization features in the other rss aggregators that he is currently using, and in his answer has included Feeds 2.0 in his list of top-five tools! Thanks Dennis!

On the other hand, David Tebbutt (disclosure: who has been our mentor in Innovate!Europe 2006) did not include Feeds 2.0 in his list! Our only option therefore was to leave a humorous comment in his blog

We were expecting a similar humorous answer from David as well, however we were even more happily surprised by his response, since he not only praised Feeds 2.0 but he also included links to the service and to his post about Feeds 2.0 at the Information World Review blog!

Thank you Dennis and David! Zaragoza was terrific fun for us as well and we hope that you know that we think you are one TWO of the nicest and most sincere people we have ever met…

Feeds 2.0 users are presented with recommendations for posts and feeds that they might want to read or subscribe to. It works by taking into account what the entire community of Feeds 2.0 readers with similar interests are finding interesting and it is based on two main ideas: Collaborative filtering and Content-based filtering.

Collaborative filtering (CF) filters information for a user based on a collection of user profiles. Users having similar profiles may share similar interests. Hence, CF exploits correlations between ratings across a population of users by first finding users most similar to some active user and by then forming a weighted vote over these neighbors to predict unobserved ratings. For a user, information can be filtered in/out regarding to the behaviors of his or her similar users. At Feeds 2.0, user profiles are collected implicitly which means that for each user his/her profile is based on passive observation and contains users historic interaction data.

Content-based filtering is an alternative paradigm that has been used mainly in the context of recommending items such as books, web pages, news, etc. for which informative content descriptors exist. Standard machine learning methods like those described in our previous post can be used in this context (e.g. neural networks, bayesian classifiers etc).

Feeds 2.0 implements a novel, unified approach for recommendations by combining collaborative and content-based filtering techniques. This combination systematically integrates all available training information such as past user-item ratings as well as attributes of items or users to learn predictions. The key ingredient is the examination of the similarity between user-item pairs that allows simultaneous generalization across the user and item attributes.

The user and item attributes are very useful especially in the, so-called, cold-start situations, that is for situations when new users or items enter the system for which little or no rating information is available. This is exactly the reason why users at Feeds 2.0 are immediately presented with recommendations when they have read (or marked as interesting) only just a small number of posts.

In our next post we will elaborate more on the Feeds 2.0 real-time Clustering feature for news items.

A lot of people ask us about the technology on which Feeds 2.0 powerful personalization engine is based. Even though Feeds 2.0 personalization algorithms are proprietrary and patentable, we believe that we can indeed elaborate on the principles of our algorithms since, after all, they represent state of the art techniques in information retrieval and machine learning.

Feeds 2.0 personalization engine is based on the principle of text categorization. Text categorization is the process of classifying documents to one or more existent categories according to the concepts present in their texts. The organization of text in categories allows the user to limit the target of a search submitted to an information retrieval system (e.g. a search engine), to explore the collection of documents, and to find relevant information to their needs without any prior knowledge about the various keywords describing topics.

You can think of the process of personalizing individual posts coming from various feed sources as a text categorization task. In this case there are just two categories: Interesting and not-interesting groups of posts. For each individual user, Feeds 2.0 assigns new posts into one of his/her interesting or not-interesting groups.

The text categorization task can in general be utilized by machine learning algorithms or computational intelligence techniques. These algorithms can be for example artificial neural networks (feedfroward networks or Self-organizing Maps (SOM) ) or more traditional machine learning algorithms like for example C4.5 decision trees, PART decision rules and Naive Bayes or Markov classifiers.

Comparing the best performance of each algorithm, in terms of classification error, experimental results have shown that artificial neural networks are good classifiers for text categorization problems. In general, the feedforward networks are distinguished as the best classifiers and the SOM networks have usually better performance than traditional machine learning algorithms.

Feeds 2.0 uses a unique combination of the principles of the above techniques. In particular, it utilizes advanced statistical natural language processing and feature selection techniques as well as proprietrary artificial neural network classifiers. Other factors are also taken into account, like for example the sources a particular user likes, or authors and topics he’s interested in. This combination provides an advanced computational intelligence framework which gives Feeds 2.0 personalization engine a classification accuracy almost equal to 100% for the individual categories of each user.

In our next post we will elaborate more on the Feeds 2.0 Recommendation feature.