Since Flickr is one of the most well-known Web 2.0 sites it is worth taking a look at what they do if for no other reason than to use it as a predictor for what the legions of Flickr clones will soon try to copy. Today we are looking at Flickr's method for selecting what it terms "interesting" photographs–purportedly without the intervention of human editors. The results are generally pretty impressive adding to the question what variable they use to distinguish compelling visuals.
"More than just "interesting," "interestingness" could potentially be a way that Yahoo! reclaims a little piece of search from Google. Today image search at both Google and Yahoo! is largely broken. Do a search for "San Francisco" at both Google and Yahoo! Image Search and you will find a hodge podge of mostly mediocre images.
Says BuzzMachine:
"What’s great about this is that it exposes not the wisdom of the crowd but the taste of the crowd"
Now for the algorithm. Interestingness is described on Flickr as:
"…an amazing new Flickr Feature.
There are lots of things that make a photo 'interesting' (or not) in the Flickr. Where the clickthroughs are coming from; who comments on it and when; who marks it as a favorite; its tags and many more things which are constantly changing. Interestingness changes over time, as more and more fantastic photos and stories are added to Flickr."
Emphasis has been added.
By hinting at the existence of secret sauce, Flickr enters the "we're more than a pretty face" and "trust us we have amazing algorithms underneath" competitions along with people like Digg. If fact it's getting to the point that if you can't work the word algorithm into your "about us" you risk being called "web 1.0"!
Looking at Flickr's description of interestingness above you get a hint at what gets a photograph selected for this distinction and here is what we (and others) have been able to determine.
- Views, internal and external to Flickr, of the photo
- Number of comments on the photo, and also who comments on the photo
- Tags applied to the photo
- Flickr discussion groups in which the photo appears
- Favorites, a.k.a Flickr bookmarking, of the photo
- Time varying behavior of the above factors
Flickr mentions "who" twice in their one paragraph description of their process, but that is a much more difficult aspect to deconstruct. However one blogger noted an absence of the amaturish photos that seem so prevalent and wondered out loud how this might be so:
"One conclusion to draw might be that the professional and semi-professional photographers who make up a minority of Flickr's users are having a disproportionate influence on the metrics that go into Interestingness because they are more active. They make more comments, mark more photos as favorites, look at more pictures not by their current contacts, and therefore their activity has a greater weight in the algorithms that choose the Interesting photos."
Flickr appears to have tinkered with their algorithm (in Feb?) and introducing a penalty for those who appear to try and game the system by uploading to numerous Flickr groups. Aocording to one Flickr user:
"…some recent changes to the algorithm devalued the interestingness of photos submitted to too many groups. This had sparked controversy with a specific kind of Flickr user affectionately referred to as a 'group whore'."…"Group whores are users who send their photos to tons of different groups in a desperate attempt to garner attention (read: views, favs and comments) which in turn would hypothetically lead to a higher level of the coveted interestingness."
Here is a debate between flummoxed Flickr users and the Flickr founder over the issue.
Flickr is right, it is an amazing new feature.
Update: Thomas Hawk adds this hypothesis to Flickr's Interesting algorithm:
One major change that has also occured with regards to interestingness (in my guestimation of course) is that averaging has been introduced for more popular photographers to prevent them from overly dominating interestingness.
tags:web 2.0 web2.0 web-20 Social technology tagging Tags flickr
June 20, 2006 at 2:25 am |
[...] Deconstructing Flickr’s “Interestingness!” (via) [...]
June 16, 2008 at 6:43 pm |
[...] Flickr doesnt go into much detail about how this works, but there are plenty of speculators who build on their hints. The end result is that without knowing anything about the photos, Flickr is able to identify the [...]
June 25, 2008 at 3:21 am |
[...] who’re left out. There’s a reason why Flickr has only ever applied the descriptor of interestingness to photos, and not the people that take them—and that reason is that the community folks over [...]
September 29, 2008 at 12:08 pm |
[...] información | Deconstructing Flickr’s “Interestingness!” en Wesley Hein 2.0 | Grupo Secrets of Explore! en Flickr | Como hacer que te cierren la cuenta de [...]
February 6, 2009 at 11:38 am |
[...] me keep a record of my thought processes as I am reading. Also, if something has a level of “interestingness” for whatever reason (even if I think that reason is dumb or irrelevant) then it just may be [...]
February 7, 2009 at 1:23 pm |
cool topic.
but from 2006 to 2009 didn’t it get updated?
July 23, 2009 at 1:46 am |
[...] and lot’s of other stuff (Wesley Hein has written about it extensively on his excellent blog here). [...]
April 18, 2010 at 5:33 am |
I use flickr since a while and have noticed a really odd property. Therefore I suspect that the Interestingness is biased by humans, i.e. flickr admins.
October 17, 2010 at 8:20 pm |
[...] it ranks our images based on how interesting they are – which is confusingly fascinating. This blog post kind of helped explain it. Kind of. Here’s what we have for you. Our 99th most interesting [...]
January 14, 2011 at 6:14 pm |
[...] Bayless I found the following article to be very helpful in answering this question. http://wes2.wordpress.com/2006/0…Insert a dynamic date hereView All 0 CommentsCannot add comment at this [...]
February 7, 2011 at 3:55 am |
[...] better solution: When Flickr determines that a photo has an elusive quality called interestingness, that photo gets all the hits. Flickr users covet interestingness above [...]
February 7, 2011 at 4:00 am |
[...] better solution: When Flickr determines that a photo has an elusive quality called interestingness, that photo gets all the hits. Flickr users covet interestingness above [...]
July 12, 2011 at 11:33 pm |
[...] quality results by clicking on the Interesting search filter, which is a magic algorithm that appears to take into account things like image views, clicks, comments, favorites and tags. If the search term isn’t [...]
September 15, 2011 at 11:48 am |
The entire Interestingness program is so vague.
Every other person has a different take on it.
Most members are confused by it. Others hardly aware of it.
Many IT professionals who have published articles say, “It might do this”, or “It could do that”…..even they are mystified.
So it leads me to conclude:
More time is spent trying to decipher and figure what it’s about than the amount of any actual usefulness gained.
So, Why have it at all?
October 16, 2011 at 6:21 am |
detroit lions long sleeve golf shirts…
[...]Deconstructing Flickr’s “Interestingness!” « Wesley Hein 2.0[...]…
December 7, 2011 at 9:33 am |
Hi all,
That post is pretty old but given the recent answers I guess it is still active. At least lots of people to wonder about that algorithm…
So to go one step ahead, I’ve published a set of statistics made on explored photos of the last 2 years: http://www.flickr.com/photos/franckmichel/6471458477/
This is not a set of tricks, but an attempt to make observations on why explored photos have in common.
Hope this helps!
Franck.
March 23, 2012 at 6:29 am |
[...] stumbled upon an interesting blog today. The interestingness starts with the blog tag line and [...]
December 19, 2012 at 5:54 pm |
My buddy actually worked at flickr and helped develop a lot of their algorithms. I’m not going to suggest I understand what they did, but I will say it’s probably not as complex as you may think. It’s well thought-out, but think about the indicators that they have available to them… clicks, likes, and think about creating a word cloud… then you’re on the right track for figuring out what’s popular within a common group.