A Social Network Visualisation Graph for a Local Business

Thanks to a couple of weeks of trying, and some major digging into APIs and other coding options... I have gathered enough data to put together a rudimentary network of FB relationships of users interacting with Lawrence Companies (LC). I've got some feedback on what that looks like, and some decisions that can be taken now that the data can be put in one place for review. I offer up a couple of options of what can be done with these types of data... after all, you never offer up just one option to a client... or potential client.

To recap, I gathered all the reaction data to LC's FB page since 2011, as well as comments, counts of shares, and mentions. I chose, for the purpose of this graph, to focus on the reactions. There were 3 times as many reactions as shares, mentions, and comments combined, and I've yet to find a way to track shares to individual accounts.

The resulting pull of friends data resulted in 18,940 data points. I forced reciprocal relationships in the data, as FB doesn't make a clear distinction between following and friends. For the purpose of this graph, the assumption is that if you show up on someone's friends list, that you have a reciprocal relationship. Additionally, this graph represents only relationships, and not conversations. I've chosen to identify relationships among those who reacted to posts from LC's FB page.

On to the data. I chose to filter based on a degree range of 6, and removed outliers (of which there were 6) with no connections to the central group. I've anonimised the graph data, because nobody wants to see their friends on FB made public. You will note there are 35 data points, but that the number 7 shows up twice. The repetition is deliberate and not an error. Employees are noted with green nodes, and non-employees with red.

The key question I had was how robust the networks of those reacting were. As stated in the previous post on this topic, approximately 20% of the volume of reactions came from employees. It's also no surprise to me that the most robust networks are employees (1,5,6,7,8,12, and 16). The selection bias of the reactions is most likely the cause... but please note 1,5,7, and 8 have very central positions in this graph... hence a lot of strong connections. The duplication of 7 as an employee and a non-employee results because of that node having multiple FB accounts, and identifying with multiple employers. Had the reactions come from larger non-employee populations, we might have seen other robust networks represented.

So... that's a lot of gobbledy-gook, telling me virtually nothing. What do I do with this thing?

You ask yourself what the objectives of your social outreach is.

I mentioned in a previous post that there are articles discussing truck driver shortages. If increasing driver applications, or increasing incoming owner-operator applications is a key measure, then perhaps working with node 8, a maintenance worker with several truck driver friends may be a good target for beginning outreach. By leveraging experience of node 16, an IT employee, LC should be able to create podcast content that can be gathered from that node's driver friends and shared through LC's main content sites. And good old node 7... that driver has a robust list of other truck driver friends that should have content directed to them. Not on this graph, but also of importance, are the three interns from LC who have reacted to posts and have a group of friends including drivers.

How that content is distributed is another conversation for another post. Let's hold off until the next post for that.

A Social Digital Idea for a Local Business

I've spent so much time in Big Pharma that I'm worried that I've gotten pigeon-holed... Okay, let's be honest, my twitter name is @bradatpharma, so I've kinda done it to myself. I think @bradateverything, though... that's a little too egotistical.

What I want to do, most of all, is find a way that I can describe how what I've worked on doing in a regulated industry for the last 25 years is transferable to other industries. This time, and probably the next couple of times, I'd like to show some of my thoughts around the transportation industry and the use of social digital media. If you've got a Facebook page, a Twitter account, or run ads on Google, what do I know that can be of any help? How can The Lawrence Companies (Lawrence) of Roanoke, VA do anything of value in the social digital space? What is Lawrence doing now that seems problematic... or at least worth a discussion? Can I make any recommendations as to what I'd like to try with them to address problems I see in the transportation industry? Well, I'll do that, and end with a recommendation of what to do with one of their social digital platforms.

Transportation and trucking... admittedly, an industry of which I know only a little, professionally. Let's start with what I know.

When I was a kid, I watched "BJ and the Bear". It's a tv show about a trucker and his chimpanzee... Bear... I know, right, it's a chimpanzee, but it's named "Bear". What's up with that? Since I was that tv-watching tot, I've wanted to drive an 18 wheeler cross-country... and have a chimpanzee. Therefore, it should come as little surprise that I've gathered, at least, a few facts at my fingertips.

• You need a CDL to drive a truck. "Shocking," you may say. But, seriously, this means that you have to undergo a regular certification process for driving a whole other type of vehicle. A process requiring written and practical skills. You have to be dedicated to do this to begin with, usually to the tune of about 3,500 USD, and have to keep up your skills. 18 wheelers on the road are driven by some amazingly adept humans.
• Trucks get things to where they need to be. You may silently, or not so silently, curse that truck driver during your commute, but how do you think the beans for your latte, the gas for your car, the clothes on your back, or the paper in your office printer got to where they are? Trucking, trans-shipping, or local delivery takes trucks and truckers.
• Trucking can often be a one person business. In addition to the skills of just driving your truck, a trucker may have multiple other concerns. Truckers can only do their job 14 hours a day. This means, if somebody took 6 rather than 2 hours to load your truck... you've lost a lot of good hours just sitting around, not making money by being on the road. If you own and operate (o/o) your truck, you're constantly doing the math on depreciation of your tires, how much fuel you're managing, or whether or not you're dead-heading a leg of this trip. They're like trading ship captains.
• Truckers are aging out, and there's not enough talent backfilling. How many times do you hear a child saying, "I want to be a trucker when I grow up," and then hear encouragement for that dream. "No, Jane, you want to go to college and become an accountant." Well, trucking is one more blue collar industry where there are not enough replacements filling the aging workforce. See point 2 for why this may be a problem.

So, I know just enough to be mildly annoying on the topic. But what does that mean from a social digital strategy perspective?

Let's dig into The Lawrence Companies (Lawrence) and a couple of their social digital properties. The company describes itself as being involved in commercial and residential moving, equipment rental, data and records management, and truck repair.

First, I did the obvious... brute force searching in Google. How do those keywords stack up against their Google results? NOTE: Do try this at home, because your results may vary. In my results, I've chosen to see 100 returns on every page. In 12 searches relating to their own company description, Lawrence doesn't show up.

So, I took to Twitter... because that's my preferred platform... and they don't show up in 4 searches related to looking for drivers or the topic of transportation... Honestly, though, that's my fault for doing the search, because they haven't posted in more than a year.

Next, to Facebook. I don't like to start there because data acquisition can be such a mess. They've got 544 posts (your mileage may vary if you check today) since they started the account. Based on the post volume, I'm gonna say they started the account in 2013. We've got 235 comments, 3,464 reactions, and 1,026 shares. Pretty good for come local content.

Once you take out the typical words you'd expect from the posts, you see:

The focus on the page is on employee recognition, concerns for their drivers (i.e. tiptuesday), promoting their services, and a lot of recommendation on residential moving.

The comments that come back tend to be focused a little differently:

From this one you see those dates, and those are answers to trivia questions related to photos. There's additionally a lot of "attaboy" type comments that are tied to the employee recognition.

Of the information I see here, there are few links directly to hiring Lawrence for any of their services. There is no consistent call to action. Nor do there seem to be calls-to-action tied to specific themes.

An additional piece of information that I didn't find until I dug into the posts is that Lawrence is affiliated with United Van Lines... Okay. So, those searches previously mentioned *do* tend to mention United Van Lines, generally in the ad portion. I didn't field test any phone calls to see if I got transferred to Lawrence... maybe I should do that next.

One of my most favorite little insights actually comes from tracking those who *reacted* to posts. So, we've got those 3,464 reactions, and when you pull them and sort them by user, you see that approximately 20% of them come from current and former employees. So, you've got an account executive from North Carolina, another Lawrence executive, a few office staff, as well as a few drivers. A nice crowd, but very little consistent reach outside of corporate environs.

I'm working on a network visualization... but I'm amazed how difficult it is to gather any relationship data from FB.

Ultimately, If I take what I know about the transportation industry, I really only see about 1 and a half of those 4 points I know anything about being dealt with in the FB feed.

So, let me offer my first idea that I would love to see Lawrence try out.

It is awesome when you call out drivers for awards and performance. Keep that up. I'd love to see two calls to action on each of those posts.

1. Ask people to add their best wishes to the driver being recognized. Ask them to share it with their friends in the industry. See if you can get a wider audience to see the drivers who are really good at their job.
2. Include a call to action for prospective driver candidates to apply to drive for Lawrence.

I've got some more ideas in the bag... but I'm gonna let those brew in my noggin to see how they shake out.

"we want health care for people not just for feeding shareholder value"

I had an interesting exchange with @stales recently. Her posit was that you couldn't mine or analyse all the data associated with a patient, so how do you improve patient journey analysis?

Tons of data is generated, but we can't possible analyze and mine it all = what are we missing? #patientjourneys

— Alicia C. Staley (@stales) June 12, 2017

You get lots of data to a system that can analyse it and then you find a trusted broker to put all that data together and figure out how to work with the appropriate parties, like Big Pharma and insurance companies.

To begin, I responded that I'm sure we can analyse it all... that's what machine learning is for. Of course, machine learning has hit some bumps with @ibmwatson lately. In my humble opinion, the issue with Watson hasn't been with the learning, but with the predicting. Machine learning is fairly standardised at this point.

A quick tutorial from a novice... feel free to skip this or correct me...

Machine learning takes samples known cases. So, let's say I want to analyse a journey of a breast cancer patient. I may want to pick data from @stales and review her:

• search terms and search agents
• social activity in twitter and facebook
• blog posts
• medical billing records
• electronic health records (EHR)
• prescription purchases

before, during, and after her diagnosis. Then I'll also pick about 50-100 or or so other breast cancer patients' data and feed it all into the program. The machine learning tool develops patterns of search terms, social posts, physician visits, prescriptions... the whole ball of wax. Then, and this is where the data gets to be useful, we take other patients who might not yet have been diagnosed, and pop their search data, their posts, their medical data into the program. As the machine learning tool identifies similarities to the baseline, the system will flag them for review. "Here's a potential match..." That sort of thing. Where this all gets dicey is if the system tries to predict what will happen next... "Well, you've done a, b, and c... so d-z may be logical next steps."

If this all sounds like I'm some fiend from insert your favourite evil technology movie here... I'm sorry. The point of data is to analyse it. WHAT WE DO WITH THE ANALYSIS IS WHAT MARKS US OUT AS HUMAN/ EVIL FIEND.

One of my other points in my conversation with @stales was that we need to have trust from patients and honesty from Big Pharma. You see, I'm assuming that Big Pharma will use the data to develop therapies which can help stem the progression of disorders, prevent disorders from occurring, or help manage the disorder until a cure can be discovered. This kind of agreement, this tit for tat, assumes that patients give up an immense amount of privacy and Big Pharma gains a metric buttload of data that helps these patients and those coming after them.

The potential legal conundra emanating from this are legion. If a bulk of unblinded health data exists, what happens when insurance get their hands on it? If predictive analysis becomes the standard, what happens when decisions are taken for continuing coverage based on the analytics? When Big Pharma can microtarget patients, what does that advertising look like? HIPAA? Will governmental agencies exclude immigrants based on health history?

Of course, I mention those things because they're already happening. Insurance companies spend a lot of money to have the most robust actuarial tables for inclusion/ exclusion criteria. Big Pharma already combs through blinded EHR data to identify markets for clinical trials or drug development. HIPAA sometimes feels like a cruel joke intended to make it harder for my data to be used by multiple physicians. I'll leave the last one alone... but google your own examples.

So, there's no clear reason to assume that Big Pharma or the insurance industry can be trusted. Unless you have a monopoly on the research, development, approval, manufacture, distribution, and payment for treatments though, there's no other game in town.

An honest, intermediate broker though... that has some legs.

If we look at the example of the Cystic Fibrosis Foundation (CFF), and their development of Kalydeco, we may have the best example of what happens when an honest broker gets involved in the patient journey.

By establishing a "Venture Philanthropy" model, the CFF was able to solicit funding which then went to targeted research clinicians who developed a drug approved by the FDA... which then went on to be marketed by a company for 300,000USD per year...

But the model exists. It's there. It got the job done... right up until that last part. So, we can modify the working model. It's what you do. You don't say, "Well, that didn't work... looks like we have to find some completely other new way to do it." You say, "Well, that *almost* worked... what failed? Let's fix that."

To that end, the trusted broker is probably going to have to come from each disease constituency. CFF showed that a dedicated group can get shit done. So, the National Multiple Sclerosis Society, American Diabetes Association, Short Bowel Syndrome Foundation, American Cancer Society, Sjogrens Syndrome Foundation, American Heart Association, Crohn's & Colitis Foundation, National Organization for Rare Disorders, and the multitude others can act as data repositories for the journey of their patients. You can guarantee that each group is staffed with a Chief Data Officer or Technology Officer or other job. Those staffers needs to lead the charge to get the data resources for their analyses.

Of course, data analysis is a back-office task. It's not pretty. It's viewed as a bunch of data-loving nerds crunching numbers, building statistical models, producing charts... like patient journeys... for other people to never read in white papers.

If we want the data for patient journeys, we have to gather and analyse the data for patient journeys. And we have to find people who love healthcare data specifically to do these analyses. You *do* fall into a flow that may make you seem like Dr. Evil while you're doing your analysis... but those of us who love healthcare data love it because we know if we find a new data point that helps identify patients early, or finds a new influencer with a new point of view, or tease out that one lab test that seems to be helping identify patients more commonly than others, or help develop appropriate pricing models... we want health care for people not just for feeding shareholder value.