So why is it, then, that a simple amusing case of 55-gallon of lubricant made so many bad headlines for Facebook?

And Facebook has more fronts to fight in its battles for transformation into a revenue-driven company. Timeline may be great for brands, but it’s a magnet for popular revolt. Besides resenting the no-alternative approach Facebook took, why are users so upset about the actual Timeline view, which is surely more visually appealing than the boring wall?

I find the answer to both relates to context.

For the Sponsored Stories it seems pretty clear. “Yes, I linked to a 55-gallon lubricant product, but I did so as a joke”, well then, Sentiment Analysis still has a long way to go with sarcasm despite some recent advance right here in the Hebrew university. Sarcasm is one extreme example, but that missing context could even just be that you’re no longer fan of that company you liked a month ago, and just didn’t get to unlike yet.

And what about Timeline? isn’t it great that all your previous statuses and photos are there, organized along your timeline and telling your story? well, it is, but only if you care to ensure that it tells the story that you really want to tell. The context of that story may depend on where we were, what we were up to at the time, who our friends were… some of this may not even be possible to reconstruct in the Timeline.

In addition, we are used to our stories dropping off the cliff of the page fold and disappearing into oblivion, so we don’t really care to update them or remove those we don’t feel so proud of anymore. Suddenly, they come back to haunt us with Timeline, and we have to scramble to adjust…

And in a final associative thought: the tiled UX of Timeline does remind me of the Pinterest-mania that has taken hold on every new social curation site. So why does this look so so much fun on Pinterest? Context again. Pinterest has none of it, it’s a pure fun/discovery experience, each tile is independent and you’re not really trying to follow up a thread, or cover all that you’ve missed since your last visit. For a social network though, that would be, well, out of context.

It took me a while to figure out my opinion, but several interesting articles got the stars aligned just right for a split second to make some sense (until some new developments will soon de-align them again ).

Take a deep breath. OK, here it comes:

Google+ is Google’s take on Social.

Yes, I know, who would have thought?…
It’s just that Google’s definition of Social is a bit different.

At Facebook (and really, for most of us), Social is about conversations with people you actually know.
At Google, Social is the new alias for Personalization.

It’s pretty simple: Google’s business model has always meant the more I know about you, the better I can monetize through more targeted ads. At first, it was all about the search engine being where you always start your surfing, and Google was well seated. As traffic to social networks grew, culminating with Facebook overtaking Google on March 2010, it became increasingly clear that a larger portion of our information starts being served to us from social networks. Google was left out.

Why was that so important? Google still had tons of searches, an ever-growing email market share, and successful news aggregation and rss reader, among other assets. That’s quite a lot to know about us, isn’t it?

It turned out that the missing link often was the starting point. You would learn about the new thing, the new trend, the new gadget you want to get, while you were out of Google’s reach. By the time you got into the Google web, you may have already got your mind set on what you want to get and even where, making the Google ads a lot less effective.

The Follow versus Friend model is also a huge issue. It means that G+ is about self-publishing and positioning yourself, and not about conversations. That suits Google very well, and is not just a differentiation from FB. This model drives you to follow based on interest, building an interest graph rather than a social graph, and being a lot more useful to profiling you than your social connections.

That interest graph, in turn, makes sure your first encounter with those things that make you tick is inside the Google web. It also links back well to the fine assets that Google holds today, from your docs to your publishing tools. So when Google News announces those funny badges, and you may have thought “Heh, who would want to put these stinking badges on their profiles…” – think again. Their private nature is just fine for Google. It’s a way to ask you to validate your inferred interests: “So tell us, is that interest of yours in US politics that we have inferred from your news reading a real inherent interest, or was it just a transient interest that will melt away after the election?“. Again – big difference for profiling.

Finally, Google+ is positioned to be a professional network. Focusing on interests and having anyone able to follow you, will keep away the teens and lure the self-proclaimed professionals. In that sense, LinkedIn may have more of a reason for concern, at least as the content network it now tries to be. It’s quite likely that G+ does not even aim to unseat Facebook, only to dry it out of its professional appeal, and leave it with what we started with – party/kids photos and keeping track of what those old friends are up to.

I guess I already know what network I’ll be posting a link to this post to…

Six years ago, when I considered graduate studies (10 years after graduating my B.Sc) I was CTO in a company that was at a crossroads, leading to very short term product and technology thinking. Looking for a change, I felt the academic world offered a space where deep, broad thinking was preferred over nearsighted goals. So I reduced my position at work, and took on studies back in the Technion.

I finished the needed courses in a year and a half, but the thesis took much longer. Friends warned me it’s difficult to context switch between work and research, not to mention family, and they were indeed right. Still, I wanted to feel the academic life again, and figure out if I wanted to pursue it full time and continue to a PhD.

The conclusion gradually distilled into a resounding No. I’ll stop at Master’s. One reason was my allergic reactions to too much maths, so prevalent in the Technion, but there was also something deeper. I realized that the user experience is where I’m at, and core computer science research is far from it, except perhaps HCI departments.

There is a significant gap between the cutting edge in academy and in practice. A paper may be worth publishing due to a statistically significant increment of 5% in relevancy (see the major interest around the Netflix prize), whereas actual users will barely feel the difference. On the other hand, stuff that is considered “commodity” in the academic world, can make big waves if implemented well in the industry, and for a good reason. Companies have built a major user following (and a fortune…) just by doing excellent and usable implementation of basic CS algorithms.

So if I have to choose between making a the research community happy, or making end users happy, I definitely choose the latter. Perhaps I’ll go back to do my PhD in another 10 years, but until then, it’s Farewell Academia!

Living on the seam between algorithm development and product management in the past few years, I’ve come to appreciate the need to be able to evaluate not just that it works, but that it works well. A search engine may return results that contain the keywords, but are these the most relevant ones? a recommendation algorithm may return products that are related to the user in some way, but can they be considered “good” recommendations?

During my master’s studies I came to know the work done over at TREC, and was fascinated by the strong emphasis on what we developers often skim over – evaluating results’ quality statistically, and moreover analyzing the evaluation method itself, to ensure that it is sound. So with that approach in mind, I teamed with our talented QA team to create a working framework in 2 days. Here are some lessons and tips learned along the way, that could be useful for others trying to achieve a similar feat:

1. Create a generic tool. TREC is mostly about search; however, with some imagination, most AI algorithms can be reduced to similar building blocks. Search, recommendation, classification – all could eventually be reduced to taking an input and returning a ranked list of results, on which the same quality metric can be applied. Code-wise, we used a generic scoring class, with a wrapping interface that has different implementations for different algos to provide the varying context.
2. Use large data. This may sound trivial in the academic world, but when you’re in a QA state of mind, you sometimes tend to get used to creating small worlds that are easy to control. Not here. It’s very important to simulate real-life user scenarios by using data that’s similar to production, so we used out integration environment, which replicates from production data.
3. Facilitate judging. Obtaining relevance judgments is crucial to getting useful tests. The customer here is a business owner / product manager, who may not appreciate the tedious task of rating results. We created a browser plugin that allows rating from within the actual results page, and accumulates those ratings in a per-test relevance file.
4. Measure test staleness. The downside of using non-controlled data is that it moves the carpet from under your feet. Data may change over time and your test may become less relevant. We used Buckley’s Binary Preference (bPref) measure that functions well with incomplete judgments, and also introduced a weighted measure of how many unjudged results are found, to trigger a test failure when results become too unreliable (requiring another judging round).

You see, in the academy we are conditioned to believe that the lower chances of acceptance, the better the venue for publishing, so if you’re willing to accept me to your club right from the start – huh, forget it!

A couple of weeks ago I got another mail from them. This time, the happy bunch invited me to be a reviewer on one of their books. Now, that was really amusing – if not a writer, then I’d be a reviewer? pathetic, I thought. But is the picture really this simple?

It was interesting, first, to see that they do actually use a peer-review system, even if perhaps not a super-duper double-blind system. And then I started wondering, is that conditioning for favoring low-acceptance publications really still relevant in the self-publishing era?

I remember when I published my first paper on AAAI, I was quite outraged at the idea that you have to pay, then to give away all copyrights, and then be used as a money bait for readers, as the publication meant I could not give free access to my own readers, unless I pay again. In a time when publishing your words on the web is such a common privilege, that seems plain wrong.

Back in the times when publishing was a costly process, high selection rate guaranteed that subscribers won’t waste their money sponsoring the print of low-quality papers. Furthermore, anything not printed had a very low chance of getting read by other researchers, not to mention cited, and so readers relied on editors to indeed include only the best. Nowadays, papers are read mostly online, and if your paper is accessible to search engines, that suffices – whoever finds your research useful will read and cite it. This Wikipedia entry has the whole story in a nutshell.

So as for myself – I still did not publish or review in iConcept press, but I am now less dismissive of this somewhat disruptive industry; not because it will win over the established venues, but because it will accelerate the move towards decentralized and online publishing, better fit for our era.

I’m overloaded. So in the past few months I’ve gradually reduced my subscription list from over 50 feeds to around a dozen, and at the same time increased my reliance on Genieo, which claims to be tracking already 537 feeds for me (though not all are ones I really would fully subscribe to, but that’s the beauty of it…)

When trying to understand what had happened, I came to realize my reader subscriptions list was made of two types of feeds:

1. Feeds that are generally on topics I’m interested in
2. Blogs where I thought the author was interesting or smart

Type #1 is, being practical, simply not scalable. There are just too many good sources out there, and not all posts in them are really read-worthy for me, even if just to skim through. So I let Genieo discover those feeds (just clicking through to some posts) and then removed them from my subscription list. It’s amazing how good it feels to safely eliminate a feed from your reader (“…yes, I am sure I want to delete!” )

Type #2 is more tricky as I would usually be interested in all of the posts even if not in my topics of interest. These include blogs by friends, and blogs by smart people I stumbled upon who seemed worth following. I also wouldn’t want Genieo (or any other learning reader for that matter) to think I’m generally interested in those more random topics and clutter my personalized feed. So I still kept this much shorter list in my reader, but I know I can visit them a lot less frequently and not lose anything.

This combination has been working well for me in recent months. Social diet hurray!

CureTogether is a site that lets you enter your medical conditions (strictly anonymous, only aggregated data are public), and get recommended for… other “co-morbid” conditions you may have. In other words, “people who have your disease usually also have that one too, perhaps you have it too?“

Beyond the obvious jokes, this truly has potential. You don’t only get “recommended” for conditions, but rather also for treatments and causes. We all know that sometimes we have our own personal treatment that works only for us. What if it works for people in our profile, and sharing that profile, anonymously, will help similar people as well? so far this direction is not explicit enough in how the site works, possibly for lack of sufficient data, but you can infer it as you go through the questionnaires.

The data mining aspect of having a resource such as CureTogether’s database is naturally extremely valuable. CureTogether’s founders share some of their findings on their blog. The power of applying computer science analytics and experimentation methodologies – sharpened by web-derived needs – to social sciences and others, reminded me of Ben Schneiderman’s talk on “Science 2.0“. The idea that computer science can contribute methodologies that stretch beyond the confines of computing machines is a mind-boggling one, at least for me.

But would you trust collaborative filtering with your health? it’s no wonder that the main popular conditions on the site are far from life threatening, and the popular ones are such with unclear causes and treatments, such as migraines, back pains and allergies. Still, the benefit on these alone will probably be sufficient for most users to justify signing up.

Seems like I’m far from the first person this happened to. It’s common enough to make it into Facebook’s FAQ.

So – no big deal, right? just had to wait a while with uploading photos from today’s trip with the kids, a little annoyance, nothing more. Then I wanted to check in the meantime what’s up on another site. Guess what I used as a login there? yep, Facebook connect. No login for you!

Facebook may be getting away with it for now, as it seems like these “maintenance” downtimes didn’t create negative buzz for Facebook connect’s position as the identity of choice for many avid FB users. But watch as more of these incidents start raising awareness to the implication of relying on Facebook as an identity provider. We’ll then realize it’s another point of failure on our way to our favorite sites, and one with no simple workaround.

Truth be told, this is not a Facebook issue, it’s an issue for centralized identity providers. If WordPress.com were down, my OpenID identity would be down just the same. With unified identity comes a unified point of failure…

“Yahoo will not use Bing. Bing is a branded search engine that Microsoft is building on top of its search back-end and we will build our own search front-end on that same Microsoft back-end. It (using Bing) is not the case, at least as envisioned at the moment”

This actually makes perfect sense. Stop spending tons of resources on crawling and ranking in a futile war with Google, and focus on building the user experience over it, leveraging Yahoo’s advantage – content. Raghavan mentions scenarios that sound a lot like Yahoo shortcuts (that’s really old news) as one example of how to deliver a more complete experience over commodity search results.

The article then goes on to discuss the second focus for Yahoo, social applications, and mentions Microsoft’s tie-up with Facebook for access to social graph. Raghavan is quoted as saying:

“Social networks are not just a place to hang out, but to get things done. It predates the web.. I’m not sure where the sweet spot is, we’re still doing research on it”

Also makes perfect sense. With Google as a common enemy, and Microsoft a Facebook partner, Yahoo may be better positioned to deliver social applications that leverage the de-facto standard of Facebook graph, rather than push its own failed networks.

So why is my post title suggesting what it’s suggesting??

There is one catch in sub-contracting your search results: you are now limited with what you can do in search ranking. The best you can do is re-rank the set of results Microsoft’s technology supplied you with before presenting it to the user. As I’ve pointed out in the past when talking about Delver’s technology, social (graph-based) search is a game that cannot be played by reranking, since it’s a classic long tail problem. So when you can’t interfere with how search results are ranked, you also can’t deliver true social search, as Google recently did. One less social application Yahoo can build…

Just finished reading Daniel Tunkelang’s recently published book on Faceted Search. I read Daniel’s blog (“The Noisy Channel“) regularly, and enjoy his good mix of IR practice with emphasis on Human-Computer Interaction (HCI). With faceted search tasks on the roadmap at work, I wanted to better educate myself on the topic, and this one looked like a good read, with the cover promising:

“… a self-contained treatment of the topic, with an extensive bibliography for those who would like to pursue particular aspects in more depth”

With 70 pages, the book reads quickly and smoothly. Daniel provides a fascinating intro to faceted search, from early taxonomies, to facets, to faceted navigation and on to faceted search. He adds an introductory chapter on IR, which is a worthwhile read even for IR professionals with some interesting insights. One is how ranked retrieval that we all grew so accustomed of, blurred the once clear border of relevant vs. non-relevant that set retrieval enforced. Daniel suggests that this issue is significant for faceted search, being a set-retrieval oriented task, and a pingback on his blog led me to a fascinating elaboration on this pain in another fine search blog (recommended read!).

With such elaborate introductory chapters and more on faceted search history, not much is left though for the actual chapters on research and practice, and as a reader I felt there could be a lot more there. But then, it is reasonable to leave a lot to the reader and just give a taste of the challenges, to be later explored by the curious reader from the bibliography.

However, that promise for extensive bibliography somewhat disappointed me… With 119 references, and only about a quarter being academic publications from the past 5 years, I felt a bit back to square one. I was hoping for more of a literature survey and pointers when discussing the techniques for those tough issues, such as how to choose the most informational facets for a given query or how to extract facets from unstructured fields. Daniel provide some useful tips on those, but reading more on these topics will require doing my own literature scan.

In any case, for a newcomer with little background in search in general and faceted in particular, this book is an excellent introduction. Those more versed with classic IR moving into faceted search, will find the book an interesting read but probably not sufficient as a full reference.