I’ve had a fairly rough 9 days with a very troublesome model. My original hypotheses are rejected. A piece of the world doesn’t really work the way that I expected. The great news is that I’m forced to look beyond the clean dataset and write new hypotheses. Even failures can be great. However, it doesn’t make for good commercial reading. Instead of having that nice, clean, nugget: Brands that did x realized y. There’s a much messier message: Neither a, b, c, d, e, f, g, h, i , j, k, l, m, n, nor p had a significant impact on y. That messier message works among marketing scientists. Usually a sound of surprise. Then acceptance when they see the[…]
Category: Social Media Measurement
Today is Steve Miller’s last day at Syncapse. He’s taking some time to enjoy the experience of welcoming his first child into the world. Steve Miller and I have worked fairly closely over the years – he as an Information Architect and myself as a Marketing Scientist. We were both part of the landmark NASA.gov redesign. Since then, we did major sites in the healthcare and retail sectors. He welcomed me into Syncapse on my first day, and since then, we’ve iterated on social media measurement experience design. His contributions in terms of usability in data driven insight generation are well reflected both in the interfaces and in roadmaps. He’s a champion for user centric design. And, I believe that[…]
There’s a DRY principle in programming, and one that is pervasive in RAILS-land: Don’t Repeat Yourself. The same should go for everybody. From commenting, blogging, to writing books. Repeating somebody’s work in its entirety is pretty unnecessary when a citation would do. What you build off others, how you do intellectual parkour and create something new out of many things old, is what’s valuable. You advance everybody that much further and faster by doing so. And a gap in the literature doesn’t always need to be filled. There might be a very good reason for such a gap. It’s finally time for me to make an original contribution because I have something original to say. There’s a gap that needs[…]
The next WAW Toronto will be on July 28. It’s being held on the second floor of Bar Wellington. It’s free to attend and You can sign up to attend here. The invite: “Developers make it possible to measure anything, statisticians and dataminers work models, IAs finesse interfaces, analysts mash and managers action. Effective Analytics takes an orchestra. Lets talk to each other and see whats possible.” Historically, WAW’s attract a strong contingent of web analysts, social analysts (many from Syncapse), IA’s, a few dev’s, recruiters, vendors, and yes, two dataminers. And it’s a great mix. Let’s keep that mix and expand it. Additional invites to business strategists, eScientists, Marketing Scientists, and specialized developers.
I’ve been heads down with the team for awhile pounding out a study examining the value of a Facebook Fan. The results of that study were presented at Internet Week on Friday morning and can be downloaded here. I have hopes. I hope it throws some wind into the sails of people who are doing good social media marketing strategy. Absolution is frequently sought in simple numbers. The importance of activation strategy should be very clear in the charts and text of the paper. The second is for the lack of misquotes. It would be really nice if it wasn’t misquoted. The third is that I hope you’ll find it useful. In sum, take a look, and feed on back.
So just what have I been up to? I’ve been dividing my time between a major initiative and product development. Much of my involvement revolves around Evidence Based Marketing – and it’s literally that deadly. It’s that level of sustainable competitive advantage. It’s like a Philosoraptor armed with an RPG, riding a shark. Yeaaaaaaaaaaah. The most interesting aspect has been the integration of measurement science with information architecture with development with creative with product development. There are continuous collisions between the desire for intuitive simplicity with utility with robust functionality with elegant design with data accuracy – all within budget and a desired launch date of yesterday. The best business models are those which you solve a problem for a[…]
I’m increasingly disturbed by the accuracy of Topic Bearing Word of Mouth (WOM) algorithms. A previous study, published in this space, expressed dissatisfaction with standard sentiment analysis. My mind has since turned to the difficulty in expressing massive amounts of WOM into simple metrics that are actionable and decomposable. So let’s just go beyond the realm of evidence based pre-optimization of marketing messages, and set the entire area of sentiment-bearing word polarity aside for awhile. It’s relevant and important. Just not the focus tonight. Let’s turn to topic bearing WOM. Imagine you could listen to the world, and assume that Burke’s reality is now…a reality. If you haven’t seen the video from my ‘about’ section – here it is again.[…]
Social media data. Huge amount of volume. Huge amount of complexity and simplicity in structure. Time for a radical metaphor. It’s like the night sky. With the naked eye, you can see thousands individual dots of light. And, humans being human, if you look long and hard enough, you’ll see patterns and start associating events with those patterns. See below. I offer some evidence to back up that claim. Of course, those relationships are one possible interpretation. (And fine. I accept where they’re coming from). If I used something significantly more powerful, like the Hubble, and trained it at a fairly dark part of the sky – (and they did) – you’d see this: Right there – next to the[…]
The Syncapse Measurement Science team put together an experiment on sentiment analysis, as applied to social media measurement. As promised: Link to the White Paper: syncapse-sentiment-analysis Link to the Data Set: The Geurilla Analytics Project _ Sentiment The paper will speak for itself. We can discuss it here and on Twitter.
The Quest for Simplicity in Social Media Measurement (#smm) is one that will dominate the year. Trying to produce something simple out of something complex is…complex. There are seven axioms that are guiding a lot of my thought in dealing with that complexity: 1. The purpose of analytics is to derive competitive advantage for the organization / firm / entity. It follows that the purpose of Social Media Measurement is to drive competitive advantage. If the end result isn’t competitive advantage – then it has no value. That unto itself is a value statement. Simplicity drives competitive advantage because simple is more actionable than complex. I’m often asked questions that have very complex comprehensive answers. I have to sort out[…]