Archive for the ‘recommendation system’ Category

ReStream Quick Tip: Add Twitter Favorites, Receive More Relevant Recommendations

Thursday, April 15th, 2010

Add your Twitter favorites to ReStream to receive better content recommendations. ReStream uses what you’ve favorited in the past as a predictor to what you like going forward. This helps improve the accuracy of the recommendation system.

Add Twitter Favorites

  1. Log into ReStream
  2. Go to your recommended reading page (click on your name in the top navigation)
  3. Click on “Favorite Tweets” in the right navigation

This will import your last 500 tweets into ReStream – assuming you have that many. Once complete, allow a few minutes, your Twitter favorites will be used to improve our content recommendations to you. Mobile: The Twitter Discovery Engine Goes Where You Go

Tuesday, February 9th, 2010

Today is launch day for Mobile. Now you can access the discovery engine from everywhere. Highlight from the new web application include:

  • Filter your Twitter stream based on links and trends
  • Receive’s content recommendations
  • View the most popular content currently being shared on Twitter
  • Highlighted content keeps you updated on what your favorite Twitter users are publishing Mobile is free. You just need a Twitter account to get started.

New Mobile Twitter App for Managing Information Overload

Monday, February 8th, 2010 Mobile is now live! Mobile is almost ready for launch. Soon you will have many of the great filtering and sharing features of every where you go.

Highlights include: Mobile
  • Real-time Twitter Stream: Transforms tweets from your stream into web page titles.
  • Twitter Trends: See what links are trending from your stream.
  • Recommendations: Receive recommendations based on your interests.
  • Most Popular: See the most popular links currently being tracked by
  • FavMe: Just like, you can favorite people. The people you favorite influences the content recommends.
  • Highlights: A highlight area shows recent Tweets from the people you’ve favorited or content recommendations from
  • Tweet, ReTweet, Favorite Tweets, and more…

The mobile web app has been optimized for the iPhone. If you would like to preview this release, please send me an email and I’ll send you a link. If you run into issues using another mobile platform please let me know. I want to make this accessible to everyone but I don’t have other platforms to test on.

Mining Twitter for Gold

Tuesday, January 12th, 2010

Finding the 27% of Tweets that Have Value

A recent study by ReadWriteWeb has shown that only 27% of tweets contain information with some value. Many people will point to this and use it to dismiss Twitter as worthwhile platform. However, this number comes from Twitter’s flexibility. Some people use it to keep in touch with friends, others use it break news. Some use Twitter for advertising and others use it for sharing information they find on blogs.

It’s this last group that’s the most interesting. It’s the human web. It’s people finding information and sharing it that adds value where search engines can not.

The problem is finding the tweets that make up this 27% of the stream that holds information of value. Further, 27% doesn’t sound like much until you realize it’s 70+ million tweets per week. The best information on Twitter amounts to a needle in haystack.

This points to the growing need for filters and recommendation engines for the real-time web. Last week I posted on micro filters and I believe this post by ReadWriteWeb further emphasizes this need.

To leverage the value that Twitter and the whole real-time web hold, we need better tools. We need more filters that go beyond the basics; Twitter lists, follower lists, and individual favorites. For example, value can be attributed to the number of people sharing the same content or  the credibility and clout of those sharing it.

If the web is going to evolve beyond search, micro filters will play a huge part in it but filters alone are not the answer.

Recommendation systems are the other piece of the puzzle. They’re needed to understand user behaviors; what people like and don’t like, what they favorite, what they read, and what they share. Recommendation systems leverage this data and combine it with filters to find the best information that people want to read. This helps us to take a full advantage of the real-time web without becoming overwhelmed.

To solve the problem of finding the 27% of Tweets that have some value, filters will be used to narrow the stream of information. Then recommendation systems, which have some insight into our past behavior, will be able to narrow the focus even further by taking the information output by these filters and funnel it to us based on our interests. This means that we’ll all be giving up some privacy on the web but it’s a trade off we’ll need to make to keep up with the barrage of information.

Automatically Receive Recommended Content from Twitter

Wednesday, December 30th, 2009

One of the problems I have with Twitter is staying up-to-date on the latest information being shared. You can’t stay connected 24 hours a day but you don’t want to miss anything either. This is what got me started on the ReStream project.

ReStream is all about finding the best information on Twitter without having to constantly stay connected.

But there is one problem.

I want to be notified when exceptionally great content that highly matches my interests is flying around on Twitter. I’m not always connected to ReStream either which is why I’ve added discovery alerts that send tweets to inform you of this great content.

ReStream Discovery Alerts

Tweets are sent from @restream once an hour – no more than 2 tweets – to inform you of the great content that you may have missed. If you’ve added tags to your profile, then there is no need to set anything up. These updates will come to you automatically.

If you don’t want to receive these updates, I’ll be adding a opt-out check box to the profile page where you can turn it off.


Please add your comments below. I’m interested to hear about what you think of this new feature.

ReStream Update: Favoriting Twitter Users, Detailed Recommendations, & More Control

Tuesday, November 24th, 2009

Today we pushed out another update for ReStream and this one is significant. Not only does it take our recommendation system to another level but it also provides more detailed information on the content that we recommend. Here’s a list of the new features before I get into the details.

  • Recommendation System Phase 2: You can now favorite your Twitter friends and the people you follow using ReStream. If there are people using Twitter that you like and respect, favorite them, and the content we recommend to you will be influenced by these favorites.
  • Detailed Recommended Reading: Each link that we recommend to you now shows the comments made about them in Twitter.
  • More Control: ReTweet and Favorite Twitter comments from the Recommended Reading column.

Favorite Twitter Users

Our goal is to build a recommendation system that truely understands your interests. ReStream helps  you retrieve the lost diamonds from the real-time river and knowing what people you enjoy listening to, following, and learning from will significantly impact the content that we recommend to you.

When we began designing the new favorites system, we wanted to do it in a way that was open and reusable for you. I love to use many different Twitter clients but it frustrates me to no end when I need to setup the same things in each system. With our new favorites system, we’ve made it open by adding all of your favorites to a private Twitter list in your Twitter account called ReStreamFavs. When you favorite someone in ReStream, they are also added to this list so you can follow and reuse the list in other applications.

One benefit of tracking your ReStream favorites in a Twitter list is that you can add and remove people from this list from any application. When you go back into ReStream, simply go to your profile page and sync your ReStreamFavs list and our database will be updated with the changes and our recommendation system will automatically leverage your updated list.

The Phase 2 update is a huge step for ReStream but we’ve got a long way to go. It will only be through your support and feedback that we can continue to make this application better. Please provide your comments below and let us know how we can help you to further explore the real-time web.