Hashtag Analytics: Comparison of Communities

Every community is different.

Take #measure and #analytics ... two seemingly similar communities, one focusing on Web Analytics, one focusing on ... wait for it ... analytics!!!

Look at this table, a table that reviews the segment users from each community belong to.  In the table, users had to participate in their community in the past week ... the data is then captured for the past four weeks:

Recency = 1 Week
	#measure	#analytics	change
Tweets = 1, Past 4 Weeks	973	1,716	-743
Tweets = 2+ Past 4 Weeks	283	406	-123
Tweets = 3 of Past 4 Weeks	87	94	-7
Tweets = 4 of Past 4 Weeks, Statements	24	35	-11
Tweets = 4 of Past 4 Weeks, Neutral	22	16	6
Tweets = 4 of Past 4 Weeks, Re-Tweeted	22	10	12
Totals	1,411	2,277	-866

The difference in the communities is like night and day.


The #measure community has 68 of 1,411 users that are "highly active".


The #analytics community has 61 of 2,277 users that are "highly active".


The #analytics community is not much of a community, in reality, with 1,716 of 2,277 participants tweeting only one time.  This is a "broadcast community".


Sometimes, simple segmentation schemes help us understand the dynamics surrounding a community.  In both communities, there is a very small audience of core members producing all of the content, combined with a large population of broadcasters.  Proportionately, the #measure community has more loyal users than does the #analytics community.




Hillstrom's Hashtag Analytics:

• Print Via Amazon, Click Here!
• Digital Via Kindle, Click Here!
• Hire Me For A Project, Click Here!

Hashtag Analytics: Removing a Member of the Community

The social media community and online analytics community do a great job of measuring things.  They can tell you, for instance, that @michelehinojosa (a popular individual in the #measure community), is influential or not influential, they can score her based on all sorts of criteria.

For some reason, nobody seems to want to answer a different question ... "What would happen if you removed @michelehinojosa from the community?"


That's what we're going to explore today.


Recall, this is a five-week forecast for the #measure community.

Now, let's have some fun.  We'll remove any activity associated with @michelehinojosa from the community.  Then, we re-segment all users, and we produce a forecast for the next five weeks, without @michelehinojosa participating in the community.


Here's the forecast!

This user has a profound influence on the community.  Let's look at the base week, week zero.

• Two users other than @michelehinojosa would not exist in the community without her input.
• Times users are re-tweeted with her = 253, without her = 233.
• Times users are answered with her = 64, without her = 60.
• Total tweets = 747 with her, 703 without her.

In other words, this user provides about 7% of the "oxygen" that carries this community.  And as we forecast her influence into the future, we see the same thing ... 5% to 6% of the "oxygen" is provided by this user, going forward ... the influence diminishes a bit as new users enter the community.


Let's look at another user ... @immeria.

This fine young man has a different type of impact on the community.  He impacts more users ... without his participation, about 2% of the community no longer participates.  He does not impact the total oxygen of the community as much, in other words, he doesn't impact the number of tweets or number of conversations.  But he does bring along 2% of the community.  And his impact lasts through the forecast cycle, meaning he impacts new participants as well.

This exercise can be run for every user in a community.  We can easily forecast what impact each user has on the overall future of a community.  By looking forward, we get to see what might happen, and we can take steps to change the future.  When we simply look back into the past, we only measure what happened in the past.

In this simple example, when we remove just two users from a community of about four hundred weekly participants, we lose close to 8% of all future activity in this community.  In spite of a ton of new users, these two folks, @michelehinojosa and @immeria, foster a wonderful and vibrant community.  That's a decent measure of influence, don't you think?


If you want to learn more about Hillstrom's Hashtag Analytics, give the booklet a try.  It's one of the top forty direct marketing books currently available on the Kindle platform!!

Purchase Via Amazon, Print:  $7.95.
Purchase Via Amazon, Kindle:  $2.99.
Hire Kevin For A Project:  Click Here.

Hashtag Analytics: Seeing The Future In The #Measure Community

Take a look at the social media measurement tools that exist, and you're not likely to see many people focusing on the future.

Some of the those in the Web Analytics Pantheon and Social Media world create spectacular tools that do a very credible job of looking back, slicing and dicing user behavior in any number of ways.  They identify those who influences the conversation.  They describe the type of conversations folks have.  They map the network a person belongs to.  We're blessed to have such interesting tools.


I'm not here to compete with that stuff ... you can't compete with it.  I'm here to help folks see what the future holds.  This, after all, is where all of the actionable strategies happen.  Think about it ... you don't care that the weather was sunny and 62 degrees two days ago, you need to plan for the weekend, so you need to know what the weather will be ... not what it was.

Take a look at the #measure community, for instance.  I looked at the community recently, taking data from a prior four week period to forecast the next week, then using the data to create a five week future view of the community.  Click on the image below to see the forecast.

What you see is a decrease in the level of participation within the community.  Now, this does not mean that the community is in decline, not at all.  It simply means that for the small time-frame analyzed, the community was less engaged than it needed to be to continue to grow in a healthy way.  In fact, because of Christmas / New Year's, the declines were much more significant than this, I had to adjust for the seasonality of Christmas / New Year's.  When I run this analysis pre-Thanksgiving, I get a different answer, a more positive answer.  When I run this analysis at the end of the month ... well, then we'll truly know where this community is heading.  

At this time, this is a medium-sized community that is very, very hard to break in to ... with plus/minus sixty folks who have joined the conversation.

Now, in every e-commerce company, somebody is responsible for forecasting sales for the next twelve months, by day.  So it makes logical sense that any community manager would want to know what the future of his/her community is, right?  This is something you don't find in any of the popular Twitter-based analytics tools.  This is my focus.  This is what I love doing, it's completely actionable, and it's an area of analysis not being explored!

Next week, we'll do something neat --- we'll remove one important user from the community, and we'll see if the absence of the individual harms or helps the future trajectory of the community.  If you are an active participant in the #measure community, please send me a user_id that you'd like to see removed in the forecast ... I'll run an example for the individual who gets the most votes.

And in two weeks, we'll compare the #measure community to the #analytics community ... competing communities doing similar work ... which community is forecast to have a stronger future?


If you agree that forecasting the future health of a community is important, drop me a line or leave a comment.  If you want to hire me to create a forecast for your community, contact me.  If you want to buy the booklet, called "Hillstrom's Hashtag Analytics", download it via Kindle, or via print from Amazon.

Hashtag Analytics: Forecasting Engagement

Over the next few weeks, we're going to dig into some of the dynamics within the #measure web analytics community.

I retrieved data for an eight week period from early November to early January.  In the analysis, I looked at four weeks of history, seeing if there were trends that helped me understand who would participate again in the next week.

I created a segmentation scheme ... thirteen existing segments that describe user behavior. This will get a teeny-bit geeky for some of you, so feel free to fast forward to the results section of the discussion if you wish.

• Recency = 1 Week, 1 Tweet Past Four Weeks.
• Recency = 1 Week, 2+ Tweets Past Four Weeks, Participate Only 1-2 Weeks of Past 4.
• Recency = 1 Week, Participated in 3 of Past 4 Weeks.
• Recency = 1 Week, Participated in 4/4 Weeks, Skew = Broadcasting.
• Recency = 1 Week, Participated in 4/4 Weeks, Skew = Neutral.
• Recency = 1 Week, Participated in 4/4 Weeks, Skew = Being Re-Tweeted
• Recency = 2 Weeks, 1 Tweet Past Four Weeks.
• Recency = 2 Weeks, 2+ Tweets Past Four Weeks, Participate Only 1-2 Weeks of Past 4.
• Recency = 2 Weeks, Participated in 3 of Past 4 Weeks.
• Recency = 3 Weeks, 1 Tweet Past Four Weeks.
• Recency = 3 Weeks, 2+ Tweets Past Four Weeks.
• Recency = 4 Weeks, 1 Tweet Past Four Weeks.
• Recency = 4 Weeks, 2+ Tweets Past Four Weeks.

Results:


The following table (click on the image to enlarge it) illustrates how the community "engaged" in a subsequent week.

Within this community, there are significant differences in subsequent engagement.

• Those who just pop-off one tweet to broadcast something are not likely to come back.
• The most engaged are obvious ... those who participated in four of the past four weeks.
• Those who are frequently re-tweeted are the ones most likely to be engaged next week, a "duh", but interesting to see, nonetheless.
• If a user goes more than two weeks without participating, it begins to become unlikely that the user will jump back in.
• A new user only has a 10% chance of being re-tweeted.
• Amazingly, new users made up 50% of those who were active in the following week.
• New users, however, only yielded 21% of all tweets & re-tweets.
• 25% of all activity (tweets + re-tweets) within the #measure community in this one week came from just 23 individuals (6%).  These folks participated in four of the prior four weeks, and skewed to individuals who are likely to be re-tweeted.

So What?


Yup, that's a common response from folks.  Well, here's what we're going to illustrate in the next two weeks.

1. Next week, I will present a forecast model that shows me how the #measure community is likely to grow and thrive in the future.  I'll show how important it is to nurture the community, to encourage folks to participate.  In addition, I'll demonstrate the overwhelming importance of new participants.
2. In two weeks, I will illustrate what happens to the forecasted trajectory of this community when one influential individual drops out of the community.

If you can forecast where your community is headed in the future, and you can understand the importance of new/valuable users, you can grow your community accordingly.
Interested in the forecasting aspect of Hillstrom's Hashtag Analytics?  Buy the book!

• Print via Amazon:  $7.95.
• Digital via Kindle:  $2.99.
• Digital via Nook:  $2.99.
• Hire Kevin for a Project!

Hashtag Analytics: A Twitter "Storm"

The weather folks in Portland, OR use #pdxtst to share information about weather-related events.  So whenever a "storm" is coming, you'll observe a "Twitter Storm"!

In late November, there was talk of a big storm coming to the Pacific Northwest.  In the four weeks prior to talk of a big storm, there wasn't much activity in the community:

Recency	Cases	Engage	# Engage
1 Week	26	34.4%	9
2 Weeks	20	20.1%	4
3 Weeks	15	13.3%	2
4 Weeks	8	29.9%	2
2 Months	38	10.8%	4
3 Months	47	4.2%	2
4-6 Mo.	254	2.5%	6
7-9 Mo.	108	1.2%	1
10-12 Mo.	20	1.4%	0
Newbies	8	100.0%	8
Percent Newbies =		19.4%

Basically, there isn't much to talk about, and this is a closed community, without many new folks participating.

And then, the weather changes.  Take a look at how the metric change as a result!

Recency	Cases	Engage	# Engage
1 Week	45	71.1%	32
2 Weeks	5	80.0%	4
3 Weeks	15	53.3%	8
4 Weeks	40	52.5%	21
2 Months	18	38.9%	7
3 Months	39	33.3%	13
4-6 Mo.	221	19.0%	42
7-9 Mo.	140	20.7%	29
10-12 Mo.	27	7.4%	2
Newbies	292	100.0%	292
Percent Newbies =		64.9%

Pow!!

Notice that engagement rates go bonkers, regardless of recency since last tweet.  The entire population is buzzing about this event!  Even more important, nearly two out of every three "tweeters" are new to the #pdxtst.


Now, we need to see what happens the following week.  Take a look at engagement rates.

Recency	Cases	Engage	# Engage
1 Week	450	6.9%	31
2 Weeks	13	0.0%	0
3 Weeks	1	0.0%	0
4 Weeks	7	0.0%	0
2 Months	21	0.0%	0
3 Months	32	0.0%	0
4-6 Mo.	137	0.0%	0
7-9 Mo.	150	0.7%	1
10-12 Mo.	31	0.0%	0
Newbies	5	100.0%	5
Percent Newbies =		13.5%

Clearly, there wasn't anything worth talking about, so the community shut down.


The following week, there's a bit more buzz, but only among recent participants.

Recency	Cases	Engage	# Engage
1 Week	37	35.1%	13
2 Weeks	419	2.6%	11
3 Weeks	13	0.0%	0
4 Weeks	1	0.0%	0
2 Months	28	0.0%	0
3 Months	28	7.1%	2
4-6 Mo.	133	0.8%	1
7-9 Mo.	154	0.0%	0
10-12 Mo.	34	0.0%	0
Newbies	8	100.0%	8
Percent Newbies =		22.8%

I'm going to show you what happens for one more week.  Pay attention to the glut of folks who participated during the winter weather event ... they've dropped down to three weeks of recency.

Recency	Cases	Engage	# Engage
1 Week	35	54.3%	19
2 Weeks	24	37.5%	9
3 Weeks	408	15.9%	65
4 Weeks	13	15.4%	2
2 Months	27	11.1%	3
3 Months	21	4.8%	1
4-6 Mo.	107	7.5%	8
7-9 Mo.	175	1.7%	3
10-12 Mo.	45	4.4%	2
Newbies	58	100.0%	58
Percent Newbies =		34.1%

Ok, there's weather to talk about this week, and the audience comes back --- but most important, there's the glut of people with three weeks of recency ... those folks engage at a normal rate, but there are so many people in this cohort that they fuel the conversation ... sixty-five people in this band engage about lousy weather.


What's the point of this analysis?


There are two key takeaways:

1. When something goes viral, you end up with a large cohort of individuals who have the potential to fuel a conversation in the future.
2. For there to be a conversation, there has to be something to talk about.  Notice how this community comes to life when there is something to talk about!

In other words, a significant weather event "awakened" this community, fueling high engagement rates, and fueling a ginormous increase in new users.  But a ton of new users/followers/fans doesn't mean anything unless this audience has something to talk about.  Counts and numbers have very little meaning ... having something to talk about is important.

Want to learn more about Hashtag Analytics?  Give Hillstrom's Hashtag Analytics a read!

• Print at Amazon.com:  $7.95.
• Kindle at Amazon.com:  $2.99.
• Nook at Barnes & Noble:  $2.99.
• Hire me for a project, click here!

Hillstrom's Hashtag Analytics: Start The New Year In Style!

Ever wonder if your Twitter community is headed for unfettered growth?  Been concerned that your Twitter community is slumping toward oblivion?

Hillstrom's Hashtag Analytics helps you answer that question.  The methodology allows you to understand what the future trajectory of your Twitter community looks like, and helps outline ways for you to increase engagement among your followers.

This is a crisp, quick 44 page read.  You'll also get two FREE spreadsheets that help you quantify the future trajectory of your Twitter-based social media community. 

Pick your format!

• Paperback via Amazon.com:  $7.95.
• Kindle via Amazon:  $2.99 (Now the 5th best selling Direct Marketing book on Kindle!).
• Nook via Barnes & Noble:  $2.99.

Why Are You Even Doing This?

Earlier this week, I shared an analysis of Nordstrom's Twitter followers with you.

The analysis was part of a larger series on what I call "Hillstrom's Hashtag Analytics".

You get a lot of feedback when you write content for close to 5,000 people, across the blog and for the folks following on Twitter.  As one might expect, you get a lot of positive feedback.


You also get a lot of indifference, and you get a lot of negative feedback.


Here's a generalized view of the feedback:

• Classic Database Marketers = Positive.
• Classic Direct Marketers = Positive.
• Social Media Advocates = Indifference.
• Social Media Haters = Indifference and Negative.
• My Catalog Marketing Audience = Indifference.
• Social Media Agencies = Positive.
• Analytics Agencies = Positive and Negative.
• Digital Marketers = Negative.
• Academia = Negative.
• Purveyors of Twitter Analytics = Indifference and Negative.
• Web Analysts = Indifference and Negative.

One person simply said the following:  "... why are you even doing this?"


I don't care if you think that Social Media is a vapid expression of digital extroversion.


I don't care if you think that Social Media is a self-evident expression of the concept that markets are conversations.


I only care about the data, about the interaction of customers within this channel.


For all of the feedback I've received, all of the criticism and praise, almost nobody commented on the three most important findings:

1. The Nordstrom community was, by and large, dis-engaged.
2. The Martha Stewart community was, by and large, highly engaged.
3. No direct link was made between engagement and profit.

All anybody wanted to argue about was whether Social Media was a crock of hoo-ha or whether it was the single greatest invention of all time or whether web analysts have already invented the tools necessary to analyze customer/user information.


I did not receive any critical feedback about the data and the findings, the comparison of the two communities, or about profitability.


That's what is wrong with marketing, and analytics, in 2010.


That's why I am doing this.


We are blinded by Social Media theories, hypotheses, and opinions, to the point that we cannot even look at the data and offer an unbiased analysis of the findings.  Heck, we don't even want to look at the data, do we?  We'd rather have an argument than an evaluation of the findings.


I lived through this, from 1995 - 2005.  I watched the catalog industry implode, not because of the viability of the business model, but because of a contempt for the online channel.  Online was a religion, you either had faith in the online channel, or you had faith in offline marketing.


What I learned from that experience was that the existing set of tools were incapable of communicating to either audience ... existing tools failed to convince online marketers that offline marketing worked, existing tools failed to convince offline marketers of the new realities and possibilities of online marketing.  In short, both parties went their separate ways, both disciplines suffered as a result.


I had to link both disciplines via Multichannel Forensics.  By and large, both sides rejected Multichannel Forensics, rejecting the concept that customers interact with products, brands, and channels in ways that are not easily measured by existing tools.  Several dozen marketers did figure out that this was important ... I was able to help those companies become more profitable, and I was able to find a way to make a good living in the process.


The same problems exist today.  Social Media advocates cannot be convinced of anything other than the fact that Social Media is glorious, and they have their set of metrics to prove their worldview.  Social Media critics cannot be convinced of anything other than the fact that Social Media is nothing more than an ego-centric version of digital extroversion, and they have sales metrics to prove their worldview.


I created a framework for having an honest discussion about how customers/users actually behave.  I realize that Social Media advocates and Social Media critics will pan the methodology because the methodology doesn't fit their worldview.  That won't stop me from continuing my research.


My job is to get you, the marketing expert, to ignore the hype and the criticism and the opinions and the theories and the hypotheses ... my job is to get you to simply focus on actual customer behavior.

Just as important, my job is to offer a roadmap for data integration.  In ten years, Social Media data will be fully integrated with our current customer database infrastructure.  I realize this is terribly hard to envision today ... go back to 1997, it wasn't easy to conceive that web analytics data and e-mail data could be integrated with the customer data warehouse, yet today, it's commonplace.  The same type of data integration will happen with Social Media.  Why not try to provide a roadmap for how this will happen?  What's so bad about that?


That's why I am doing this.


Now, go buy the booklet, or hire me for a project.  Go!!!

• Paperback via Amazon, $7.95.
• Amazon Kindle, $2.99.
• Barnes and Noble Nook, $2.99.