Rojo, the web-based RSS Aggregator I’ve used ever since I gave up hope of Bloglines ever stepping up its functionality, has just come out with some more enhancements. About a month ago, they re-designed their site and now they’ve done another overhaul and added 3 new features – one of which (relevance) I will drill down into below. In a nutshell the 3 new features, as described to me by Rojo CEO Chris Alden, are:
“Rojo Mojo: Voting meets RSS – Vote for the top stories and blog posts of the day with one easy click. Each story now has a title where you can give it some mojo – and see how many other votes it’s received. The stories with the most mojo (votes) will appear on Rojo’s Today page and are factored into our relevance metrics (See Rojo Relevance below).
Rojo Relevance: Feed Reading 2.0. You’ve always been able to sort stories by date, now you can sort stories by relevance and quality too. Other feed readers only allow you to see stories in chronological order—we give you a quick way to find the most interesting stories fast by bringing the most tagged, read and mojo’d stories to the top. Rojo Relevance is smart feed reading; the more you use it, the smarter it gets. It’s our way of helping you sip from the firehose.
Rojo Categories: a range of categories in Rojo Today such as politics, entertainment, sports, Web2.0.”
The feature I like best is Rojo Relevance, because that’s precisely what I want a next-generation RSS Aggregator to do – find me the most relevant stories. I’ve used the word ‘filter’ a lot this year to express this need.
Rojo actually had a ‘relevance’ option in the previous version, so I asked Chris what has changed. He replied:
“First, the purpose of “relevance” is to do for feed reading what smart search engines (like Google) do for search results — figure out what to put on the front page. Many readers are overwhelmed by the number of new stories coming from their feeds every day. So Rojo Relevance is about sorting those by “relevance” rather than date, to put the good stuff on top.”
Ah good, so it’s like tech.memeorandum and it’ll serve as a kind of ‘newspaper frontpage’ for my feeds. Excellent! But how exactly is Rojo doing this? Chris Alden told me:
“How do we do it? Generally, just like Google used link metadata to determine relevance of search results, there is a fair amount of metadata we can use to infer relevance, including how many people are reading, tagging, and voting for a story, how popular the feed is — both to you personally, to your contacts, and to all readers, as well as things like link data and content analysis. Since Rojo is a social network as well as a reader, we also know what stories are getting read, tagged, voted for, etc. from your contacts and can factor that in too.
I won’t go into the specifics of the formula we use to generate our relevance ratings because not only is it our secret sauce but it is also something that is constantly being refined. The relevance should improve the more and your contacts you read, tag, and vote for things. What’s cool is how we use Rojo mojo — that is our voting system — to inform our relevance. With digg, for example, you can see what pages are getting the most votes in aggregate from the whole community. With Rojo, we show you what stories are getting the most votes on Rojo Today. BUT we can also show you what stories FROM YOUR FEEDS are getting the most votes. It’s sort of a personalized digg.” (emphasis mine)
Personalization has been getting a bad rap from developers this year, especially Memeorandum’s Gabe Rivera who has told me repeatedly that personalized aggregation is a very hard problem. Gabe isn’t trying to solve it with his products and to be fair he’s given me very compelling reasons why. In any case, Rojo seems to be trying to tackle the issue and it’s interesting that Chris namechecks web 2.0 success story digg – because they too will be releasing personalization functionality this year. Kevin Rose told me in a recent ZDNet interview that it is “one of our top priorities”.
Finally, as to what has changed in Rojo’s relevance formula, Chris said:
“The ‘relevance’ view shows the most relevant stories from ALL of your feeds. What’s new is that virtually EVERY view can be sorted by relevance. So you can look at ONE feed and sort it by relevance, instead of date. Or you can look at a group of feeds — say feeds you’ve tagged “web2.0” — and sort that view by relevance. You can even sort our tagged stories view by relevance (tagged stories are stories being tagged by Rojo users.) Also, with the launch of the Rojo mojo voting feature we are factoring in “mojo” in our relevance formula.”
All in all, this looks to be very useful new functionality. I’ll need to have more of a play to be certain, but any RSS Aggregator that is making an effort to tackle the ‘attention’ problem of 2006 is alright in my book.
As I mentioned at the start, this is Rojo’s second major re-design in a couple of months. Rojo’s previous re-design was mixed for me. It had a nice look and feel, but I wasn’t that impressed by the ‘Rojo links’ – an internal linking system that seemed to me to be encouraging a ‘walled garden’ approach (keep the users inside the system). But this functionality update is much more to my liking, especially the relevance feature. It’ll help keep them (ahem) relevant in a crowded market, as Mike put it.
Final thought: I wonder if this will wake Bloglines out of their slumber? 😉
Originally published on ReadWriteWeb (archived copy)