Welcome!

Industrial IoT Authors: Elizabeth White, Stackify Blog, Yeshim Deniz, SmartBear Blog, Liz McMillan

Related Topics: Agile Computing, Industrial IoT, Open Source Cloud, Cognitive Computing , Machine Learning , Cloud Security

Agile Computing: Blog Post

Using Taxonomy to Drive Online Contextual Advertising with Sophializer

Classifying Web Content to the IAB Taxonomy

It’s a Big Market …
…  online advertising.  There are 10,000 stories and data points about it.  Here are two to give some context to the journey below.  First, global online ad spending is projected by ZenithOptimedia to exceed print ad spend by 2015 (note 1).  This 2015 projected spend figure for online advertising is $132.4 billion.  Second, global online ad revenue is projected by another research agency, Digital TV Research, to hit $143 billion by 2017 (note 2).

These are prodigious amounts of money for companies to spend to connect with customers.  But … surely it’s easy to connect online customers to web content featuring, or suggesting, products? And surely, online is “better”?  Where can, and do, taxonomy-based approaches add value to this dance of moving (emotional and semantic) parts between the intentful consumer poised to shop and the intentful marketer with honed content?

Online Ad Targeting is Easy … so 'They' Say …
Really?  So what might be “easy”?  And, indeed, “better”?  Let’s unbundle these simulacra that look like very fuzzy concepts, and as ontologists and knowledge engineers let’s think our way forward with the concept of “precision”.

So … online is more precise than billboards by freeways?  Lightly stated, online has advantages.  What about magazine print ads vs. online?  Online has potential advantages. But … and this is a very big but … in both these cases (and all others) online depends on connecting potential customers to products, their features, their benefits, their attributes and so on precisely, and with precision that is repeatable and extensible.  Rather than random (random is the most expensive way to advertise and has fallen out of favor).  And, since online copy and online ads are words (including in videos) and are semantically classifiable, and since classifications can be organized into models (taxonomies and ontologies) … then there are advantages to be created through the combination of semantic analysis, categorization and taxonomy.

Now, let’s connect taxonomy, classification, semantics and optimizing online ad targeting.  There are a host of holy grails currently being sought in the web/mobile/social uber-ecosystem.  Some are well found, though not perfect, and are unlikely to traverse through a paradigmatic improvement.  Think ‘search’.  Others are most definitely not found (yet).  Given the size of the market outlined in the first paragraph, the rewards are huge to those with the tools and skillsets that know how to work with semantics, taxonomy/ontology, classification of content to taxonomy, and design of taxonomies to drive online targeting.

New Approaches to Classifying to the IAB Taxonomy with Sophializer
Sophia Search
is a recent entrant into this space.  (I have written about them before here.   Sophia Search’s tool – currently called the ‘Sophializer’ – categorizes any URL to nodes in the Internet Advertising Bureau (IAB) taxonomy.  Sophializer can also classify content of ads (and so create a semantic/conceptual ‘signature’ for each). The IAB Contextual Taxonomy comprises three levels:

  • Tier 1 – 23 nodes
  • Tier 2 – 371 nodes
  • Tier 3 – unspecified and vendor specific

Given that Sophializer categorizes both sides of this content dance – web page and ad – web properties can serve ads to any page automatically using the IAB taxonomy as the cross-mapping conceptual foundation.

Sophializer not only classifies to Tier 1 and Tier 2 it also discovers/generates robust classifications that can be used to customize Tier 3 for individual customers.

Benefits of Using Taxonomy for Ad Targeting
Taxonomy gives a framework to this kind of semantic work.  Essentially, we are cross-mapping both partners of this content dance – content and ad - using the IAB taxonomy  as a “choreographer” of sorts.  Other taxonomies could be used.  In fact, multiple taxonomies could be used – and this would be particularly powerful if these taxonomies were cross-mapped to each other.  For example, if you have content (web page, say, or ad) categorized and mapped to Taxonomy A and Taxonomy A is cross-mapped to the IAB taxonomy … then … you can propagate these ads to content that is already categorized.

Benefits of Using Categorization Tools to Assign Marketing Content to Taxonomy Nodes
There are a number of different methods of assigning content to nodes in any taxonomy –

  • Manually
  • Training sets of documents (training documents are most often manually selected as exemplars)
  • Categorization algorithms that work with semantic tokens

There is more than enough to say on each of these around methods, workflows, best practices and pitfalls for a blog post on each.  But not here.

Sophializer utilizes patented and proprietary algorithms in the core of their categorization engine.  Two fundamental points are worth, briefly, focusing on.  Firstly, different categorization engines use different patented technologies.  “Quality” from different categorizers is (very) variable.  Which is why it is important to carry out “Proofs of Concept” when evaluating this technology.

Secondly, the more semantically rich the taxonomy – e.g. fully enriched with synonyms and other types of evidence terms – the better “quality” one gets with any method of associating content to taxonomy nodes.   Both of these parameters are make-or-break (literally) in using semantics to target online ads.

Learn More 2.0
The Google Display Network is IAB Certified and complies with the top 2 tiers of the IAB Contextual Taxonomy.  You can read details of what Google do here and this also navigates you to the Google mapping to the IAB taxonomy Tier 1 and Tier 2.

Sophia Search currently has a number of engagements on the web that are live.  For example, targeting ads for non-fiction books (from a major publishing house) to news stories (on a pre-eminent news site).  You can contact them for details.

This is not an empty space.  Other companies are also searching for the holy grail of taxonomy-based content targeting mediated by content categorization that works.  See, for example, see ADmantX (http://blog.admantx.com/post/15726823528/a-new-iab-based-taxonomy-and-an...).

This whole space is an excellent example of where the application of the nexus of taxonomy, categorization and semantics will provide stratospheric business benefit.  Grails are waiting to be found here.

Notes
Note 1.  See ZenithOprimedia

The detailed ZenithOptimedia figures can be found here

Note 2.  See Hollywood Reporter

You can download the Digital TV Research press release about these figures here

IoT & Smart Cities Stories
The deluge of IoT sensor data collected from connected devices and the powerful AI required to make that data actionable are giving rise to a hybrid ecosystem in which cloud, on-prem and edge processes become interweaved. Attendees will learn how emerging composable infrastructure solutions deliver the adaptive architecture needed to manage this new data reality. Machine learning algorithms can better anticipate data storms and automate resources to support surges, including fully scalable GPU-c...
Machine learning has taken residence at our cities' cores and now we can finally have "smart cities." Cities are a collection of buildings made to provide the structure and safety necessary for people to function, create and survive. Buildings are a pool of ever-changing performance data from large automated systems such as heating and cooling to the people that live and work within them. Through machine learning, buildings can optimize performance, reduce costs, and improve occupant comfort by ...
The explosion of new web/cloud/IoT-based applications and the data they generate are transforming our world right before our eyes. In this rush to adopt these new technologies, organizations are often ignoring fundamental questions concerning who owns the data and failing to ask for permission to conduct invasive surveillance of their customers. Organizations that are not transparent about how their systems gather data telemetry without offering shared data ownership risk product rejection, regu...
René Bostic is the Technical VP of the IBM Cloud Unit in North America. Enjoying her career with IBM during the modern millennial technological era, she is an expert in cloud computing, DevOps and emerging cloud technologies such as Blockchain. Her strengths and core competencies include a proven record of accomplishments in consensus building at all levels to assess, plan, and implement enterprise and cloud computing solutions. René is a member of the Society of Women Engineers (SWE) and a m...
Poor data quality and analytics drive down business value. In fact, Gartner estimated that the average financial impact of poor data quality on organizations is $9.7 million per year. But bad data is much more than a cost center. By eroding trust in information, analytics and the business decisions based on these, it is a serious impediment to digital transformation.
Digital Transformation: Preparing Cloud & IoT Security for the Age of Artificial Intelligence. As automation and artificial intelligence (AI) power solution development and delivery, many businesses need to build backend cloud capabilities. Well-poised organizations, marketing smart devices with AI and BlockChain capabilities prepare to refine compliance and regulatory capabilities in 2018. Volumes of health, financial, technical and privacy data, along with tightening compliance requirements by...
Predicting the future has never been more challenging - not because of the lack of data but because of the flood of ungoverned and risk laden information. Microsoft states that 2.5 exabytes of data are created every day. Expectations and reliance on data are being pushed to the limits, as demands around hybrid options continue to grow.
Digital Transformation and Disruption, Amazon Style - What You Can Learn. Chris Kocher is a co-founder of Grey Heron, a management and strategic marketing consulting firm. He has 25+ years in both strategic and hands-on operating experience helping executives and investors build revenues and shareholder value. He has consulted with over 130 companies on innovating with new business models, product strategies and monetization. Chris has held management positions at HP and Symantec in addition to ...
Enterprises have taken advantage of IoT to achieve important revenue and cost advantages. What is less apparent is how incumbent enterprises operating at scale have, following success with IoT, built analytic, operations management and software development capabilities - ranging from autonomous vehicles to manageable robotics installations. They have embraced these capabilities as if they were Silicon Valley startups.
As IoT continues to increase momentum, so does the associated risk. Secure Device Lifecycle Management (DLM) is ranked as one of the most important technology areas of IoT. Driving this trend is the realization that secure support for IoT devices provides companies the ability to deliver high-quality, reliable, secure offerings faster, create new revenue streams, and reduce support costs, all while building a competitive advantage in their markets. In this session, we will use customer use cases...