A dialog of thoughts and ideas about software, usability, and products, with random science and wacky ideas thrown in for good measure.


I sometimes hear that social sites like Facebook and Twitter will be heavyweights in the future of recommendations (or of search itself), the idea being that your friends can give you better recommendations for things like books, movies, music, and travel than random strangers can. I respectfully disagree.

First, it's hard to imagine this being the future when searching on sites social network sites is so abysmal. On Twitter, searches only go back 7 days. And while Facebook lets you search for friends, it has no decent way of searching the content of wall posts. I had to dig around pretty hard when I wanted to re-find an awesome song that a friend posted months ago.

Technical feasibility aside, there are conceptual issues with relying only on friends for recommendations. Social networks don't have the "long tail" that other sites on the Web support. For example, I have about 300 friends on Facebook, and these people tend to come from similar backgrounds as me: for the most part, we attended high school or college together, or we've worked together. Or we're related. I might value my friend's opinions on good books for summer reading, but if I'm trying to stretch my horizons, my friends are a terrible source of input, since we're so homogeneous.

Relying on Facebook or Twitter for recommendations will only benefit the socially rich, those who have thousands of diverse connections. For the rest of us, we'll have to rely on the diversity of people who aren't connected to us, but who can still influence our decisions: the people on Amazon, TripAdvisor, and other sites who tell us how good a certain book is, and what's wrong with that hotel.

The other thing that makes social network sites unsuited for recommendations is the fleeting nature of posts. On Amazon or TripAdvisor, other people's recommendations are associated with the desired object itself. But in social networks, your friends' recommendations are associated with your question. If you post a question when no one is looking, no one will answer it. If you post a question a few days after a friend posts a similar question, you won't benefit from those recommendations unless you're somehow aware of them.


I'd like to see improved search capabilities in Facebook and Twitter (why can't I search my friends based on location?), but it'll take a lot of work to rend recommendations from these sites.
3 comments:
Brad Rosenberg said...

Interesting post Dave, but I have to disagree with you on a few points. Social networks are still in their infancy, and we're just beginning to unlock their power.

I guess it comes down to what you mean by a Social Network. A Social Network doesn't need to be Facebook (personal connections). Social networks pop up through all sorts of services, the crowdsourcing of Stack Overflow, the Hive Mind of Ask Metafilter, the blogging community of LiveJournal, the power of Digg. The New Digg recognized that there wasn't just one face to recommending popular news stories, your news is now personalized based on who you follow (tastemakers, friends, etc.), propagating out from source to populace. Foursquare allows you to see what your friends are checking out, but will also tell you whats locally trending. Social as part of these websites are not just trying to use your local social network, but are trying to build out your distant connections, weak ties, and the global network as well.

It also depends on what kind of recommendation you're looking for. Looking for a local dentist? Sure, I value the opinion of my local friends, but I also value the opinion of those 2 degrees away (with a little less trust), and the wisdom of the crowd of the local community (but not any one individual that I don't know specifically). Looking for a book recommendation? I'm happy to leave that up to a Recommender System that's learned my preferences.

I guess what I'm saying is that while pre-defined expert opinion is worthwhile in many instances, systems that help me discover tastemakers personalized to me as well as let me spam my group of friends who I've learned to trust will triumph in most instances over a straight global search a la Google. This is why Google is nervous about the social space and trying to make inroads.

By the way, Facebook does have some pretty simple search functionality. Just go a type something in the upper search box and click the little search link. You can restrict your results to People, Pages, Groups, Apps, Events, Web Results, your friend's posts, everybody's posts, and filter down by post type (links, wall updates, notes, videos, photos) and geographic area.

David said...

Interesting, Brad! Your point about trusting your friends, or friends of friends, for local dentist recommendations is a good one. But I also wonder whether this can invite unintended focus on a doctor who one friend really liked, and that friend, perhaps a bit of a maven, has spread the recommendation of that dentist to his friends, who agree and pass on the recommendation... while an even better dentist happens to not be evaluated by this set of friends. A local maximum, essentially. But, since networks of friends are probably not isolated from others, perhaps a global maximum might be identified?

Brad Rosenberg said...

Sounds like a paper title, "Social Networks as a form of Global Optimization"

Post a Comment