TRENDRR Features that continue to Wow Me

Posted by Marshall Sponder on August 30, 2011 | Link It

The other day I wrote about TRENDRR.TV and covered most of the features – but I neglected to point out TRENDRR.TV is built on TRENDRR.COM and is an extension of it.  There is also,  a Best Practices page, to help with the setup and a Dictionary that helps one understand the terminology used in reports.


There is a curation capability built into TRENDRR.COM twitter feed that allows for geo-location by a city/state or DMA.

TRENDRR.COM makes selecting a DMA for Geo-location of tweets fairly easy (see above), the result appears to be accurate, as well.  There are also many other dashboards one can configure with TRENDRR.COM (see below):

At this point, most of the dashboards do not show any results for me (they need to be configured), but they’re there to have just that done, providing a lot of additional information.

Creating a new project is made easier by providing custom data feeds by type of project (below)

For example, selecting a “book” project, your asked to input among other things, the Amazon ASN number for Sales Rank.

Other types of projects ask for different inputs and I haven’t explored most of them, or how the data is charted, but the platform design suggests that additional data sources and project types can be easily added to the system, as needed; that the TRENDRR platform can be customized to TV (say TRENDRR.TV) but it could also have been just as easily customized to Pharmaceutics, for example.

I don’t think, however, the level of customization in TRENDRR.TV would be easy to achieve without custom work by WiredSet to get best results.

What I think TRENDRR.TV shows me, is that any industry vertical could, theoretically, ask WiredSet to create a customized version of TRENDRR for them, and it would end up being every bit as good as TRENDRR.TV is, today.

TRENDRR also has a “Mashup Manager” that allows you to take any projects you have created and add additional data feeds from Ebay, Facebook, Foursquare, Gowalla, YouTube,  GetGlue, etc.   I did not do much with that part of TRENDRR yet, opting to think about what I really want to track, as just adding datafeeds doesn’t seem to be the best way to work with TRENDRR.

 



Habits & Familiar Locations / Haunts of Foursquare Check-ins

Posted by Marshall Sponder on August 28, 2011 | Link It

Been thinking about all the Geo-location data I’m collecting in Radian6 around 4SQ check-ins.   Truth be told, I started tracking check-ins to see if I could do, more or less myself, what Dave Kerpen had a team of 6 staff members doing with his Likeable Social Media book (his team attempted to put a hint to download a free chapter of his book, or buy it, into every bookstore in the country).

Not sure what the results of that attempt to use a social media clan to harness popularity did – but his book ranks very well on Amazon, esp in the Web Marketing Category.

But I quickly gave up on the idea, not because I could not do it, it was simply my approach is different, I’m an analyst, not a marketer.   I can get others to do marketing for me, but fundamentally, my work is with revealing truth, not spreading it.  I let the quality of my content take care of itself – too busy creating content to worry about putting hints all over the internet – but, I admit, Dave Kerpen, in attempting to use Foursquare the way he did, developed a service with is probably useful to other book marketers as a product, in and of itself.   Still, that’s not where I wish to go (or really can go, to be honest).

Rather, I began to look at the data I was collecting, care of Radian6, who provides me with an Influencer Account allowing my mind to roam – which is what I present to you today.

Before you is all the check-ins from Foursquare over the last 3 months that have been capture, mostly on Twitter.  Based on my numbers (any mention that has “4sq.com” in it) there are roughly 7 million check-ins that take place a month, over the last 3 months.

For some reason, possibly due to changes I made in the topic profile, the latest volumes aren’t up to what they were for most of the 3 months, but I think you can see check-ins tend to peak during weekends, particularly Saturdays (not unexpected).

My queries are based on what I’m finding in the data, but admit they could be expanded – I don’t claim they are as good and clean as they could be – and therefore, these numbers presented in the charts below, really depend on the queries, which will differ from analyst to analyst – there is simply no standard yet, that exists on query writing.  It’s a young field yet, Social Analytics – as I pointed out in my book.

Still, there’s not much you can do with the information unless your willing to segment it into categories,  and even subcategories.  In fact, the more categorization on can do on data, providing your categorizations are useful and fit the use-case your after (and I’ll have to explain that some other time) your data will become much more actionable.  Without the categorization, its almost next to useless.

Here goes – I managed to categorize about 30% of all the check-ins I have been collecting in Radian6 over the last few months (decided not to resize the screen so you can see it in it’s full size).

 

Doing this wasn’t that hard, and generally speaking, working with Geo-located data has some advantages in that context and structure, to some extent, is provided by the check-in, itself.   Looking at the River of News for each category gave me, more or less, satisfactory results.   Had I had another 20-30 hours I could have whittled away and categorized the 2/3 of check-ins that are left, but I didn’t bother to do that.

A couple of observations – since we know the total number of check-ins was 19,307,702 (19.3 million) then

  1. 4% of all check-ins were about Mayors (awarded/ousted, etc).
  2. 5% of all check-ins were about Badge activity (awarded/achieved)
  3. 2% of all check-ins was about arriving @home and relaxing (finally)
  4. 2% of all check-ins was about Sports Activity (of some sort)
  5. about 1/2 of a percent of check-ins was about being @work (but more could be done here with a fuller set of linguisticVariants - see chapter 3 of Social Media Analytics)
  6. Restaurant/food/dining out has the most check-in activity at 5% of all check-ins.
I could go on, but my point is  - there’s opportunity to data-mine  these breakdowns (they are more actionable – because they have context); aside from word-clouds, there’s Influencers that can clearly be picked out based on Twitter Following.  I do admit,  using a crude metric such as Twitter Followers, for someone who checked into a Museum, is probably not an indication of real interest in Museums, or that if the person really does influence others in that sector – all it shows is potential reach (and I talked about the problems of using crude metrics and suggested alternatives in my Technorati interview a few weeks ago).
But once you have done the segmentation (along the lines of what Gary Angel suggests is called a “Two-Tiered segmentation” the Radian6 data on Foursquare check-ins, becomes much more interesting than it might ordinary be.  It’s much the same as most Social Data, without that work in intelligently categorizing it, its not good for much – but for the most part, people don’t seem to understand that or be willing to pay for it, yet.
Worse yet, they pick the entirely wrong technologies to work with and totally miss the boat, hiring the wrong people, looking for results based on very shaky assumptions, and work.  But what is new?!

With the categorization on Travel (above) which covers at 5% of the total travel segment (21,653/469,160) – done via Foursquare and using simple pattern matching – I now can use the Radian6 demographics and actually get something out of it – because now I have context, something that is usually missing, out of the box with most of the social data.

The most popular age group (25-34) has 2436 records, which is about 11% of the 21,653 identified, and perhaps, less than 1% of the total mentions for travel (but it’s a sample, and 1% might be enough for our purposes).

I was able to get some data from a word cloud by first honing in on “domains mentioned” which just showed Foursquare (as expected).
But, when we look at people in NYC and continue to use Radian6 Insights data, we pick up very little information – the platform is still maturing and can’t seem to scale well beyond 2 dimensions, in most cases, it will all depend on the data sources.
I was more interested in going back to what I achieved by segmenting the check-in data, in the first place.

I looked for a Cable TV/Network segment, perhaps to go with the TRENDRR.TV post I did yesterday (another is coming, tonight). Focused on MTV and did another word-cloud.
You can keep on going down, further and further, in what I admit is a manual process of digging and find nuggets of gold.
The real issue with Radian6, and probably something that can’t be entirely fixed, is the interface design, itself.
For measurement, one would have wanted clustering (automated, to the extent that AI can kick in) but due the fundamental design of the platform, one has to dig, and dig, and dig, which is time consuming and not particularly scalable (you have to do it over, and over and over again, every time you do a new project, a new report, you have dig as if you have never done it before).
So, in this sense, Radian6 was an excellent source for me to visually collect data (what it was designed to do) but is not built to automate sub-segmentation  - the very thing that would finally make the data “actionable”.


Still, thanks to Radian6, I have collected a wealth of Geo-located Foursquare data that can be extremely useful, if know what to do with it.
Remember, check-in data is much easier to segment than other types of social data – we already have context – where they checked in; plus we usually have a short string that is semi automated and easy to run text-analytics on.
There’s so much data in my segmentation that I’ll probably write some more about it in a few days or weeks.  And when you start daisy chaining Salesforce data into Radian6, esp my example of Wealthbuilder, the other day – you could, potentially get something that is so hyper-targeted as to be almost scary.
But we’ll leave that for another post, another time.



Review of Social Media Analytics

Posted by Marshall Sponder on August 28, 2011 | Link It

Happy to announce a glowing review of Social Media Analytics appeared at the  SEMANGEL blog (Gary Angel, CTO of Semphonic.com, who also contributed to Chapters 7 and 8 of my book).

Gary picked up on, perhaps the most salient points I wanted to make in my book, here are some quotes from his review.

But that’s really just a small piece of the total effort. Marshall covers A LOT of ground in Social Media Analytics. The book starts with a broad discussion of Social Media but quickly dives down into targeting, handling internationalization issues, mining social intelligence, tracking Fans and Followers and understanding their value, measuring influence, scorecarding, content creation, monitoring technologies, and data convergence.

In almost every section, you get Marshall’s unique strengths as a writer: his enthusiasm for the topic, his hands-on approach, his passion for conversation and listening (the breadth of contributors to this book is pretty impressive), and his surprisingly practical perspective on things.

Sometimes I worry that whatever gifts I have as a writer (which is more or less, simply writing as if I was talking, thinking aloud) would stand in the way of the material I  present – or that people who read my book, would view me as a gifted communicator, but not a real hands on Analyst, which I am.

… after all, lots of people out there talk the talk …. take your money, and give some quick, pretty sounding advice, then walk away to the next engagement (everyone… quick, think of some names, I’ll not supply them here).

I didn’t do that – nor would I – and would not write about Social Media Analytics if I had not “touched it”.

I managed to get a real hands on Analyst, Gary Angel, who liked the book, say so – succeeded here – communicating, I hope, difficult material in a way that was meant to be easy for readers (which my  McGraw-Hill editors frankly preferred – they wanted to make sure my readers could consume the content – not make it too hard to read).  That’s not to say we compromised on the material – we just made sure the average reader could comprehend it (my editors constantly were “on it” making sure every point was explained in a way that made sense not only to me, but to them).

Here’s more from the Semphonic Review:

In the past few months, for example, we at Semphonic have been helping bootstrap a global social media effort for a giant technology company. We’re spearheading the measurement piece and, even in its early stages, it’s involved us in a complex set of novel and challenging issues around internationalization. So the problems of internationalization are fresh in my mind, and yet I would have never have expected them to show up as Chapter 3 in a book on Social Media analytics. Too practical and too problematic I would have thought.

No so. As in all of the chapters, Marshall not only talks the talk, he walks the walk. He used a variety of tools as he explored the topic and he talked to people (not me in this case) who were obviously deeply enmeshed in the practical difficulties of international, multi-language, multi-cultural social measurement. He gives a great overview of what types of difficulties you WILL encounter if you try to do something in this area.

Chapter 3 was very hard to write – in fact, both chapters that Gary Angel mention where the hardest chapters, the hardest writing I have ever done.

Chapter 3 and Chapter 10 each have about 100 hours of writing devoted to them, when all is said and done (research, edits, rewrites, corrections, additions, etc). What I came to see is that the problems of Internationalization and Multi-Cultural listening are the extreme cases of the same issues that permeate all listening systems – context, meaning, locale, slang, influencer identification in content, regional variations, etc.

Not only that, but I was struck by how some people around me, probably unintentionally, seemed to trivialize the effort – as if it was something one could do internally.  I made it clear it could not be, it’s too difficult a nut to crack.  I could say more about this issue of internationalization but I’ll stop here.

Gary enjoyed chapter 5 (value of fans/followers/friends) which to me, wasn’t perhaps, the chapter that sticks out it my mind – yes, it was hard to write, but not nearly as hard as Chapter 10, which he also liked.

Interestingly, Marshall echoes Bob Heyman’s theme in another really good chapter – Monitoring Tools and Technologies. The discussion here is one Marshall is particularly well-suited for because he tries everything and so has a completely realistic sense of actual tool capabilities and claims.

The part I’m talking about, however, isn’t in the excellent discussion of why check-box approaches to product comparison/selection are inadequate (I particularly enjoyed the great discussion of the stupidity of comparing the number of sources crawled claims made by Listening Tool vendors as if they were real or meaningful), it’s the part about how we staff and hire social media measurement functions.

Listen to this: “…I have come to believe marketing and communications agencies are not the most appropriate entities to measure marketing or PR campaigns run on behalf of their clients, especially within social media. Too often there is an inherent conflict of interest, as MarCom firms measure their client’s online buzz, and data can be skewed, often unintentionally, to show the successful completion of agreed-upon campaign goals.”

That’s exactly what Bob and I walked away from our conversation thinking and talking about, and Marshall is right that it’s an EVEN BIGGER mistake in PR and Social than it is in the relatively “hard” disciplines of online marketing.

Gary Angel, of course, was referring to my interview with Giles Palmer, CEO of Brandwatch.com, a monitoring platform often discussed in my book, that took place last November in Brighton UK.  It took me about 20 hours to record and transcribe the interview.   The interview was edited quite a few times, by Giles first, then by me, then by McGraw-Hill editors, and then finally, by me, putting the finishing touches.

Giles Palmer’s interview was one of the crowning achievements of my book – finally, a listening platform vendor sat down with me and shared how his platform was built from scratch.   I won’t say Giles description of how Brandwatch functions is exactly the map that every listening analytic platform has, but it is probably similar, since all the of platform vendors, including Radian6, Sysomos, Alterian SM2, and so on, face similar problems and have come up with more or less similar solutions.

But I would have been hard pressed to get anyone from Radian6, or Alterian, who would have gone on record and talked about how their platform was built, how many servers they have, how many pages they crawl each day, how many sources of data to they have, how many scientists they have on staff, or how they extract meaningful data from a lot of noise, navigational elements and ads on pages that are being crawled.

I doubt Chris Newton at Radian6 would have had that conversation with me, or any one at Alterian – in fact, they’d probably avoid it – because many see the details of how data is obtained a trade secret.  You don’t even know how much of the data that is being gathered is being bought from aggregators, vs. crawled by the monitoring platform directly.

Kudos to Giles Palmer for going where no one else would  (though Brandtology was a close second, in their interview in Chapter 3 – they talked real, as well).

I knew practically no one would give me this information, that I sought – and so I made it point to get it anyway – and I succeeded (as least, as much as I could have).

The other part of Gary Angel’s quote about my book relates to Marketing Communications firms, and I feel, it speaks for itself.  It’s based on what I personally have seen and experienced – much more thought needs to be given to this area – but I, at least, came out and said what I had to say (about it).

Also liked what Gary had to say about the book, overall:

Social Media Analytics is a great overview of the fieldSocial Media Analytics is a great overview of the field, with far more in-depth tips and tidbits than you’d reasonably expect in such an easy to consume package. In a field changing daily, Marshall’s ear-to-the-ground approach delivers something that is remarkably up-to-date and current. And his combination of hands-on approach (just getting the seemingly inexhaustible list of tool choices is valuable), careful listening, and clear-eyed perspective consistently deliver valuable insight on the real issues of social measurement. In a field changing daily, Marshall’s ear-to-the-ground approach delivers something that is remarkably up-to-date and current. And his combination of hands-on approach (just getting the seemingly inexhaustible list of tool choices is valuable), careful listening, and clear-eyed perspective consistently deliver valuable insight on the real issues of social measurement.

Now, when is Gary Angel going to write his bookthat’s one I really want to read (read all his blog posts at Semphonic religiously).



UPCOMING SPEAKING

The inaugural Social Media Analytics Summit is the first ever two-day business conference with a complete focus on social media analytics. Social media analytics enhances customer service, improves brand and reputation management, and measures overall social media success for businesses