Media covering Preventive Medicine also talk about…

Click to zoom. Note: Preventive Medicine is part (leaf) of Medicine and Health (stem) in our taxonomy.

Preventive Medicine next to what other Editorial Classifications?
In France? In the US?

Preamble:
Radar charts above are made to show the Top 6 editorial classifications and their respective weights. Data are for the week from June 22nd until June 29th 2020.

Here’s a more detailed view:

Click to zoom

Interesting to notice within the Top6:

  1. Unsurprisingly, Media in both countries are focused on Medicine & Health, but Pharmacy & Drugs is almost as high as Preventive Medicine in the US (Way less in France).
  2. Media in the US are Personal, Family and Care, when France talks Disease, Dermatology and Dentistry/Odontology
  3. In the US, right after Medicine & Health is Economy & Enterprise, heavy on Employment & Unemployment, Communication and Career. Health has a strong link on Jobs. Not present in France
  4. In France, right after Medicine & Health is Politics, heavy on Political Party, Civil Defense, Public Services and Administration. #6 in the US with Public Services at the same level.
  5. Lifestyle is present in both countries. Only with Kids in France, more classical Lifestyle with Home and Eating & Drinking in the US.
  6. Healthcare is only present in the US, heavy on Hospital & Clinic while Sports is only present in France with Fans/Community and, unsurprisingly, Football and Cycling

Why it’s important

Avoiding:

In these uncertain times, you might want to avoid content related to the current pandemic, so instead of managing the unmanageable, always out-of-date, black list of keywords, simply add the following condition to your Corpus, export/connect to your DSP… voilà.

Targeting:

If you choose to target the Medicine & Health > Preventive Medicine content, it’s important for the consistency of your brand to know what type of content is within the Media you will authorize in your white list or your PR effort or what kind of content you choose to analyze.

Questions? Tell us!

Introducing Religious Orientation in Media

Learnings on Editorial Coverages: Media Spotted as Religiously Oriented in the USA vs France.

Last week, we announced the new Spotting of Political Orientations, this week, we’re introducing the new spotting of Religious Orientations in Media!

All these analytics where done on the period 3/17-6/17/2020.

Today, we are looking for coverage of the following religions:  Buddhism, Christianity, Hinduism, Islam and Judaism, deliberately listed in alphabetical order as, should it be necessary to mention: In no way, we are pushing, nor valuing any religion, one vs another, or in general.

Above, we are comparing the Editorial Classifications of Media spotted as Religious in both, USA and France.

We can see Editorial classifications are very similar except for Economy and Enterprise, only in the USA and Medicine and Health, only in France.

What makes Media Spotted as Religious different?

In the USA:

Here, we are comparing ALL media vs those spotted as Religious, both in the USA.

The Top 6 Editorial Classifications for Media spotted as religious:

. Has Society as #1
. Shares the same Top 3
. Does not have Sports and Entertainment and Leisure
. Has Economy and Enterprise and Humain Sciences

In France:

This time, we are comparing ALL media vs those spotted as Religious, both in France.

The Top 6 Editorial Classifications for Media spotted as religious:

. Like in the USA, has Society as #1
. Unlike in the USA, does not share the same Top 3
. Does not have Tech and Sports
. Has Human Sciences and Medicine and Health

Country vs Country+Language

Next, we had a look at the difference between a language and the same language spoken in a specific country.

The Top 6 Editorial Classifications for Media spotted as religious in English, in the USA vs anywhere:

. Same Top 3 but stronger in Society and Politics in the USA
. USA has Economy and Enterprise
. Anywhere has Law

The Top 6 Editorial Classifications for Media spotted as religious in French, in the France vs anywhere:

. Same Top 6
. Stronger in Society, Lifestyle and Politics in France

How is Christianity covered?

Now, let’s focus on one religion. We picked Christianity, out of Buddhism, Hinduism, Islam and Judaism because its coverage is the largest within both countries.

 

The Top 6 Editorial Classifications for Media spotted as Religious > Christianity in both countries:

. Both have Society as #1 with heavy scores. 
. Both have Lifestyle, Politics, Human Sciences, Culture and Arts
. Only France has Medicine and Health
.Only USA has Education.

Interested? Let us know below:

Introducing Political Orientations Spotted in Media.

Learnings on Editorial Coverages: Far Left vs Far Right and US vs France.

New: We can now spot Political Orientations in Media! In a coming post, we will explain how we are able to do this.

In today’s post, we decided to analyze extremes in the Political spectrum, Left and Right and in France and the USA (we only considered editorial classifications greater than 1%):

Today, we’ve also decided to start with some of the learnings and give you more depth afterwards. (Let us know if you liked it?)

Mouse over to zoom. Click to full screen

Editorial coverages in both countries

Far Left: #1, Politics, #2, Society
Far Right: #1, Society, #2, Politics.

Politics+Society =
In the US: 46.3%, Far Left, 48.8%, Far Right
In France: 24.7%, Far Left, 29.3% Far Right

Political Party is a Far Left thing.

Political engagement high for both wings.

Unions but in opposite wings: Far Right in France and Far Left for the US

Lifestyle in both wings but covers Child, Teen and Youth in France and Masculine in the US.

Only Far Left in both countries covers Home

Editorial coverage specific to the US.

Both wings cover LGBTQ and Religion.

Both wings cover both Civil and Military Defenses.

Only US Far Right does not cover Foreign Affairs

Both wings cover Law > Constitutional and Criminal. Far Left also covers International

Both wings cover Human Sciences > Philosophy

Editorial coverage specific to France.

Both wings cover Immigration and diversity

Only Far Left covers Social and Labor

Far Left does not cover Medicine and Health

Far Left does not cover Human Sciences


In more depth:
Spotted Far Left in France

Politics – 14.9%
Public Services (Social/Health) – 9.1%
Foreign Affairs – 2.1%
Government – 1.7%
Political Party – 1.2%
Society – 9.8%
Political Engagement – 5.1%
Immigration and Diversity – 2.1%
Law – 9.1%
Social and Labor – 6.4%
Economy and Enterprise – 9.0%
Economy – 1.5%
Employment and Unemployment – 1.0%
Medicine and Health – 6.3%
Care – 3.2%
Lifestyle – 5.8%
Child, Teen and Youth – 2.8%
Home – 1.3%

Spotted Far Right in France

Society – 19.2%
Political Engagement – 8.2%
Misc News – 4.5%
Religion – 2.5%
Immigration and Diversity – 2.0%
Politics – 10.1%
Foreign Affairs – 2.7%
Political Party – 2.6%
Public Services (Social/Health) – 1.5%
Civil Defense – 1.3%
Government – 1.2%
Lifestyle – 6.9%
Child, Teen and Youth – 2.0%
Medicine and Health – 5.4%
Veterinary Medicine – 1.2%
Care – 1.0%
Economy and Enterprise – 4.8%
Union – 2.1%
Economy – 1.2%
Human Sciences – 3.9%
Philosophy – 1.2%
Psychology – 1.1%

Spotted Far Left in the USA

Politics – 29.8%
Political Party – 12.5%
Foreign Affairs – 6.9%
Government – 5.1%
Public Services (Social/Health) – 2.5%
Military Defense – 1.5%
Civil Defense – 1.0%
Society – 16.3%
Political Engagement – 7.7%
LGBTQ – 3.4%
Religion – 2.1%
Economy and Enterprise – 8.5%
Economy – 5.1%
Union – 2.9%
Law – 5.5%
Consitutional -2.7&%
International – 1.4%
Criminal – 1.0%
Lifestyle – 4.5%
Masculine – 2.8%
Home – 1.0%
Human Sciences – 3.9%
Philosophy – 2.5%

Spotted Far Right in the USA

Society – 26.6%
Political Engagement – 7.5%
Religion – 6.9%
LGBTQ – 5.4%
Misc News – 2.7%
Humanitarian Aid – 1.4%
Politics – 22.0%
Political Party – 8.9%
Government – 5.2%
Public Services (Social/Health) – 2.1%
Military Defense – 1.4%
Civil Defense – 1.2%
Law – 6.5%
Consitutional – 3.3%
Criminal – 2.2%
Lifestyle – 5.2%
Masculine – 1.5%
Medicine and Health – 3.8%
Care – 1.0%
Human Sciences – 3.7%
Philosophy – 2.6%

Got questions? Contact us!

Editorial Intelligence to find your communication targets.

The case: How, from a list of URLs, can I optimize my communication?

To preserve the confidentiality of those involved in this real business case, we will not share any name or URLs

In our exemple hereafter, the client, ACME Co., has compiled a list of article URLs related to its brand. We could use this list as is but ACME is also scoring every article with a popularity number made of mix of likes, retweets, comments…

All in all, we start with a list of URLs compiled by a client, with or without scores.

1. Editorial profiling for each URL.

For each and every URLs, TrustedOut returns the top editorial classifications.

2. Classifications/score weighting and taxonomy consolidation.

Per article, classification split and scores are weighted. Then, to align with the taxonomy, the 3 hierarchical layers are consolidated:

3. Tree Mapping learning.

We use Tree Mapping to get a visual of the table above.

TrustedOut Editorial Tree Mapping
Click to full screen

Here are some key learning:

3.1 People #1. Priority to Political Engagement

People is the biggest classification branch and Political Engagement should definitely be a priority. For campaigns, PR and watch.

Interesting, as well, are 2 related classifications: Series in Culture and Arts and TV/Videos/WebTV in Entertainment and Leisure.

3.2 Then, is Politics. 3 major classifications echoing People’s Political Engagement.

Very interesting, to see, way above, Political Engagement in People first and then 3 classifications of the same stem, Politics from the General branch.

Public Services, Civil Defense and Government are totaling 38,500, that’s almost 95% of the People’s Political Engagement (40,800).

It becomes easy, to orient your communication to resonate on this insight.

3.3 Sciences is all about Medicine and Health. Don’t miss Pharmaceutical and Drugs.

Same stem, Medicine and Health, 3 classifications with 2 clear split in importance: Pharmacy and Drugs and then, Care and Fluid.

Clearly, Pharmacy and Drugs, bigger than each Politics and half of the top notch Political Engagement, should be a focus.

3.4 Industries: All about Healthcare. 2 top classifications.

Interesting to see top 2 are, by far, Hospital and Clinic and Pharmaceuticals, both in Healthcare. 3rd and far behind is Manufacturing and Retail > Tobacco.

Interesting insight as well is to see the Industries > Medicine and Health > Pharmaceutical being half of Sciences.

Sciences first, then Industries helps with the agenda of your communication and branding efforts.

Bottom line: Focus on People and Sciences, knowing what to talk about for each.

Use the following insights for your communication, ad campaign, PR effort, Internal/External engagements…

> Tone: People and Sciences first.

> Address People’ Political Engagement knowing the 3 matters in Politics

> Approach Sciences’ Pharmaceutical and Drugs and develop on Healthcare.

> Have an eye on popular series and videos

Intrigued? Reach out!

New TrustedOut.com is here.

A new version of TrustedOut.com is now available!

As our technology and commercial offers continue to evolve, posts are no longer enough and we had to update our site as well.

We decided to re-organize our site in 2 groups:

Where, Why, How:
Vision, Benefits, Technology.

Our Vision is to make Trusted Content a utility, so everyone in any organization can tap into content they trust and thus, trust any decisions made  from it. More…

Our Benefits are coming from our AI-Powered Classifications which brings no-biais, always up-to-date universal expertise to profile any piece of content. This provides unmatched advantages vs keywords, such as Editorial Orientation and Evolution over time. More…

Our Technology is proprietary Machine Learning for Tailor-Made AI-Profiling. It’s all about datasets permanently updated for internal and external classifications. More…

Who:
Solutions for Business Intelligence, Business Watch, Online Ads, Publishers.

4 dedicated pages to the solutions we provide to 4 different type of customers:

For Business Intelligence Analysts: 

What we are fixing for Business Intelligence:
Cannot trust what’s out of your BI Tools if you do not trust what’s in.
How we are fixing it:
Feed your BI tools with content profile you define.

Read Solutions for Business Intelligence…

For Business Watch Users:

What we are fixing:
How to align Executives, Collaborators and Partners with Company Goals?
How we are fixing it:
Feed your RSS readers and newsletters tools with Corpuses from your BI Tools.

Read Solutions for Business Watch…

For Online Advertisers, Agencies and Publishers

1. Brand Safety: What we are fixing:
How can we make sure a Brand is totally safe?
How we are fixing it:
Build and Manage your Whitelist with your definition of what is safe for your Brand.

2. End of Cookies: What we are fixing:
How to target audience in absence of cookies?
How we are fixing it:
Grab Intelligence from the targeted article’s classifications.

3. Reporting laws: What we are fixing:
How to deal with government reporting laws such as the Avia law?
How we are fixing it:
Report Media with their profile made by TrustedOut. AI-Powered. Unbiased, Universal and always Up-to-date.

Read Solutions for Online Advertising…

For Publisher’s Executives and Editors:

What we are fixing:
How am I perceived? How do I compare? Are my Editorial efforts visible?
How we are fixing it:
Get instant Profiles on a Media, a Source and/or Articles.

Read Solutions for Publishers…

Questions? Let us know!

Must read posts.

1. Our vision:

Trusted Content as a Utility

  • Distrust in Media is a major, major issue.
  • No trust in content, No trust in decisions made from it.
  • Trusted Content should be like water or electricity: A Utility.
  • Define the content you trust for every segment of your business.

Trusted Content as a Utility

2. Our unique technology.

2.1 AI-powered classifications vs Keywords.
Editorial Orientations detection.

Going beyond a 1-Dimensional access to knowledge

AI-Powered Classifications are adding 2 more dimensions: Editorial orientations and timing context.

Read the full post to see example of a single event treated in 3 different ways in 2 different countries

AI-powered classifications vs Keywords. Part 1/2: Editorial Orientations detection.[updated]

2.2 AI-powered classifications vs Keywords.
Evolution over time.

For content selection: AI-powered classifications can sense Editorial Orientations AND Evolution over time. Keywords cannot.

Perception of an event evolves with time, so do our AI-Powered classifications.

How can AI-Powered Classification do this?

In a previous post, we explained how our AI worked:

How our AI-powered classification works.

Every new article is classified as follow:

Why it matters.

What’s true at publication time might not be at analytics time, or advertising time…

AI-powered classifications vs Keywords. Part 2/2: Evolution over time.

Questions? Ask!

AI-managed taxonomy to keep up with language evolutions.

Measuring against datasets.

We explained in the following post how our classification works:

How our AI-powered classification works.

For the taxonomy, words from articles are measured vs Classifications datasets (a.k.a. Bags of words)

To gauge how a media is perceived, we, this time, measure what is said vs Perceptions datasets


Matching and weighting are making the score of the document. This is how we know where an article belongs and its level of expertise/severity.

AI to keep datasets permanently relevant.

The perception we have on an event evolves over time. So should the classification of this article. To make it happen, we keep the datasets always up-to-date. As seen in last week post, the classification of an article evolves with time:

AI-powered classifications vs Keywords. Part 2/2: Evolution over time.

 

The evolution domino effect: Languages impact datasets, which impact taxonomy.

The way we talk about something evolves with time. In fact, the dialect of the tribe made of people concerned about something evolves over time. More specific, cooler, geekier, newer… whatever is the reason, we love changes, we love new ways to express ourselves.

Datasets updates. Permanently.

Datasets must be rebuilt and updated permanently to catch new words, new importance on words, up and down, and the disappearance of some.

Overlapping intelligence. On watch.

As datasets evolve they may make a classification overlap over another which will weaken the taxonomy.

We measure overlapping, permanently as well, and if one is detected the taxonomy evolves consequently.

Recommended (re)Read:

Trusted Content as a Utility

AI-powered classifications vs Keywords. Part 1/2: Editorial Orientations detection.[updated]

Questions? Shoot!

Economy and Enterprise – US vs France Taxonomies.

France’s Economy and Enterprise Taxonomy.

Let’s ask TrustedOut, for France, what is the Taxonomy of all media covering the “Economy and Enterprise” Classification group over the past 7 days.

Here’s the corpus query:

Showing 373 Medias and 750 sources

and the taxonomy DNA:

USA’s Economy and Enterprise Taxonomy.

Let’s ask TrustedOut, for the US, what is the Taxonomy of all media covering the “Economy and Enterprise” Classification group over the past 7 days.

Here’s the corpus query:

Showing 1,961 Medias and 3,645 sources

and the taxonomy DNA:


Comparisons:

France USA
General, 43.6% General, 41.9%
General > Economy and Enterprise, 20.2% General > Economy and Enterprise, 21.5%
General > Economy and Enterprise > Economy, 6.2%
General >  Finance, 5.2% General >  Finance, 5.4%
General >  Law, 6.5%
General > Tech, 8% General > Tech, 8%
Industries, 22.2% Industries, 19.1%
Sciences, 6.7% Sciences, 7.7%
People, 27.3% People, 31.2%
People > Culture and Arts, 7.3%
People > Sports, 6.6%
People > Lifestyle, 5.9%

How to read the table above: The percentage means how much of the classification datasets are in the publication. Ex: In the US,  media covering Economy and Enterprise have also 5.9% have words belonging to the classification Lifestyle which is part of People.

In France, media covering “Economy and Enterprise” also talk:

Deeper in Economy
Law
Culture and Arts
Sports

While, in the US, media covering “Economy and Enterprise” also talk:

Lifestyle

Fine tuning your corpus to compare apple to apple.

Want to compare countries for a product launch but do not want the Lifestyle classification in the US?

Simple add the IS NOT Lifestyle taxonomy:

Voila. Now run your analytics on those 2 corpuses or/and Get the corresponding whitelists…

Questions? Contact us!

 

 

Fine tuning your corpus to perfect analytics and build brand consistent whitelists.

Let’s have a look at some cool product updates our alpha-testers can enjoy since last night.

Demo scenario: Let say we want to create a Corpus for the US Food Market for some analytics on our brand and a new ad campaign coming right up.

1/ The broad definition. Country and Taxonomy.

Add country, select United States.

Add Taxonomy IS made of these two classifications :

  • Industry > Manufacturing and Retail > Food and Beverages
  • People > Lifestyle > Food and Beverages Services.

As you know, TrustedOut also profiles the level of expertise and the sensitivity on news for each media over the period of rolling time the taxonomy is computed. Here we want ALL levels and a taxonomy, stable, over the past rolling quarter (-90 days from today). We do recompute and update everything permanently.

We have 4,003 media for our Whitelist and 10,027 sources to feed our analytic tools with.

2/ Refining the target. Excluding a classification.

For this effort, we do not want media specialized in Food Processing, profiled over the same period of time, so we exclude it from our Corpus like this:

  • IS Industry > Manufacturing and Retail > Food and Beverages
  • IS People > Lifestyle > Food and Beverages Services.
  • IS NOT Industry > Agriculture > Food Processing

We now have 487 media and 732 sources.

3/ Hand picking media we do or do not want. By name, by URL.

(this is an example. nothing personal for those sites 🙂

From past experiences, we do not want to work with anything related to foodnavigator.com and its subsidiaries, neither do we want a site named “Food processing”. Clicking on “Get” and Scrolling through the media list TrustedOut gives me, I see they, indeed, are in the list:

Let’s remove them.

Let’s tell our corpus to add the following conditions:

  • Name DOES NOT CONTAIN “Food processing”
  • Website DOES NOT CONTAIN “foodnavigator” in its domain

Voila. 484 media and 726 sources.

Corpus is ready to feed our BI Analytic Tool and be our whitelist to imported in our DSP.

Questions? Shoot!

 

 

How our AI-powered classification works.

We receive a lot of questions about how our AI-powered Classification is working, so we decided to make 2 drawings to explain how it works.

1. The Taxonomy.
Gauging the media from the Inside.
Including expertise and sensitivity.

A media has sources which each publishes new articles. From every new article, we solely keep useful words (no stop words such as “the, is, but…”) which we call an “abstract”.

Every single work of this new abstract is matched vs several hundreds of datasets. Every single classification in our taxonomy has its own dataset.

Each 1 million abstracts, this means 75,000,000,000 operations.

This method is close to the tribe model. Every tribe uses a dialect made of words signing this dialect. When you recognize a dialect, you recognize a tribe. Here is a classification. Depending on the number and the weight of words, we are able to gauge the level of expertise in the classification. This gives us a score for the article.

Playing with the length of past days, we can also gauge the sensitivity to news for the sources. Compiling sources tells us where the media stands.

Bottom line: We have a universal taxonomy, always updated and able to be filtered by expertise level and over 3 periods of time to sense time sensitivity (and trend forming, but we’ll tell you more real soon)

2. The Perceptions.
Gauging the media from the Outside.
How is a Media “spotted as”.

“Fake news”, “Junk science”, and other toxic appreciations are tangible. Rarely, can this be intangible (for sure), because those are up to appreciations. What is “fake news” to some people, is not for others. This is why we treat those appreciations as “spotted as”, or “perceived on the internet as”.

Same as for our taxonomy, perception is an appreciation, but where taxonomy is about the publisher itself, we call it the Publisher Inside, the perception is the Publisher Outside, or how the publisher is perceived for those terms.

To do this, we collect how the publisher is perceived on the Internet, strictly excluding any publisher properties.

This gives us pages and words which we match with Perception datasets (one for “fake news”, one for “junk science” and so on) in a similar way explained above.

We then have a score which when above a threshold make the publication “spotted as fake news” for example.

Bottom line: We sense how a publication is perceived as not one person or group can make any universal statement.

Questions? Shoot!