Persai Gets Close to What I (and Others Will) Want

Album Cover: Abbey Road

"She's killer-diller when she's dressed to the hilt."
The Beatles / Polythene Pam

Posted on February 21, 2008 11:58 AM in Blogging
Warning: This blog entry was written two or more years ago. Therefore, it may contain broken links, out-dated or misleading content, or information that is just plain wrong. Please read on with caution.

Almost two years ago, I wrote the following about the concept of adaptive aggregators or feed readers:

Let's say [my feed reader] allowed me to give each post I read an optional "thumbs up" or "thumbs down" (similarly to how user comments are now handled over at Digg). That would teach my feed reader my reading habits over time. When these habits are better understood, it wouldn't be unreasonable to automatically hide posts from the feed that probably aren't of interest to me, or at least make them less visible so skimming through a long list of posts would become more manageable.

Since then, I've heard relatively little about any advancements in this area until today. Over at Buzzfeed, I stumbled upon mention of Persai, which bills itself as "a content recommendation system that learns from user feedback and can better recommend content."

I spent a little time reading through some coverage on Wired, catching up on (and subscribing to) the company's blog, wondering why the heck they bungled the "ai" in their logo, and even letting them know I was interested in a beta invite.

After all that, I can now say with relative confidence that Persai is the closest thing to what I envisioned in 2006 and still look forward to putting to use some day. However, where they fall short is that they set up content streams based on keywords in which a user is interested. They aren't a feed reader, but more accurately a feed generator (you can subscribe to feeds of their content recommendations in your feed reader of choice).

So why is this not quite good enough? Well, it's great that I can say I'm interested in Firefox and over time, see more and more Firefox content that I'm interested and less of the crap that often shows up in such general feeds (trust me, I know from experience). However, if I already know that I'm interested in everything Robert O'Callahan has to say on the subject, how does that help me in Persai?

Another thing I'm not clear on is whether or not subscribing to the feeds from Persai actually allows me to accept and reject content directly from my feed reader. If not, this is a big weakness, because it means I have to use their web app specifically for training their algorithm — something I'm not likely to do.

In summary, it appears that Persai is a big step in the right direction and will hopefully get more people thinking about how adaptation can make content much more useful to more people. As bigger fishes in the pond, like Google and Yahoo!, learn to aggregate the implied interests of their user bases (or, better yet, can infer such information from open platforms), we'll hopefully start to see this type of adaptation become more prominent on the web.

In the meantime, I'll still be here waiting for a feed reader to come along that wants to get to know me.

Comments

lmpnguss on May 15, 2017 at 5:23 AM:

Post Comments

If you feel like commenting on the above item, use the form below. Your email address will be used for personal contact reasons only, and will not be shown on this website.

Name:

Email Address:

Website:

Comments:

Check this box if you hate spam.