Where does Audiense extract insights from?

 

How is Audiense able to extract insights?

Our approach is to compliantly use publicly available information, using our own algorithms and third party sources to enrich that information to surface deep audience insights.

From what sources?

We gather data from a variety of social networks (Facebook, Instagram, YouTube, Twitter) and public censuses on a granular and aggregate level. However, as anyone who truly understands the Social Data industry, Twitter is the largest open platform. For instance, more than 200M Instagram, Facebook and YouTube posts are tweeted every month. 

Social Analytics vs Social Data

It is very common for Social Analytics to be used interchangeably with Social Data. Social Analytics is a means to provide performance analytics of brands on social. A few of the  most common metrics are the number of fans, followers, impressions, etc. which are easily accessible regardless of network (including Facebook and Instagram). 

Social Data on the other hand focuses on surfacing community insights, exploring conversations and/or campaigns. For example, Unmetric is considered a social analytics tool exclusively whereas Audiense would be considered a Social Data tool, and then there are platforms such as Pulsar that do both. 

Within Social Data we are able to differentiate between the type of social data under scrutiny whether it be Conversation Insights (e.g. Pulsar, Crimson or Brandwatch) and Audience Segmentation and Insights (Audiense). 

Are your findings statistically significant if they are predominantly derived from Social Data?

Think of Audiense Insights as a survey targeting the most relevant people in your audience. If you are new to statistics, you may be surprised to learn from a sample of 17,000 people you attain a margin of error of less than 1% and confident level of 99% for any audience size. To learn more about statically significant samples we recommend you go to http://www.raosoft.com/samplesize.html

When you create audiences with Audiense Insights they are usually made up of a sample size of 250,000 people, depending on the filters and the criteria applied, which is far more than the required sample of 17,000.

It’s no secret that the use of social is more prominent within the younger generations. As a result, when analysing an Audience of over 60s, it is essential to be diligent and cross-verify the insights extracted from a variety of sources.  

It is important to take into account that the insights we provide are always compared to a baseline that is relevant to your audience. This comparison increases relevancy as any biased (social data) influences both datasets, suggesting any over or under indexing attributes are highly specific and relevant insights for your audience. 

Our audience coverage varies geographically, but there is almost always a statistically significant sample of data to extract valuable insights from. We have developed functionalities that allow you to access all the available data in order to find a significant sample of your target audience.

The basis for generating insights

Generally, through machine learning, Audiense infers audience insights according to public interactions (tweets, follows, likes, etc.), the public information available within profiles of the users (name, profile photo, time zone, location), other public aggregated information (demographic census for specific segments based on surveys and other digital interactions) or a combination. Each insight has its own accuracy, but no ML is always 100% accurate.

We/our partners (IBM Watson) train models with real examples. For instance, my profile bio or my handle can indicate what age range I fall into. After training the models with thousands of real examples we look out for correlations with other characteristics (it could be photos, relationships, names, public census, etc.) in order to attribute age to individuals that haven’t been explicit. This is the basis for machine learning and those correlations can sometimes be common sense or explicit derivations whilst at other times be indirect correlations. Learn more by watching: https://www.youtube.com/watch?v=R9OHn5ZF4Uo. 

How each tab is calculated

There are certain variables which we/our partners train their algorithms with which are considered to be highly weighted but not exclusive to:

  • Segmentation: relationships between people (e.g. follow, reply, like)
  • Auto-naming: profiles self-description 
  • Demographics: photo profile, explicit locations, self-descriptions, public censuses, name, relationships, timezone, social posts.
  • Socioeconomics: age, interests, self-descriptions, public censuses
  • Interests: social posts, relationships
  • Content: social posts
  • Personality: posts, psycholinguistics
  • Buying Behaviour: social posts, psycholinguistics
  • Online Habits: photo profile, explicit locations, self-descriptions, surveys, name, relationships, timezone, social posts.
  • Multichannel - Activation: social posts, relationships

 

Other FAQ’s

How do you link profiles to different networks?

The only compliant ways to do this are:

  1. Gather information directly from the user with their consent
  2. Utilise public data 

 

The basis for generating insights

If you are using Audiense Insights, without knowing, you have become an amateur (if you aren’t already a professional) consumer researcher. We say amateur because as you probably guess there are different academic careers and degrees to become a professional consumer researcher, and you should hire one, or an organization, when you can justify it, to complement our insights. An important thing you have to know about is the difference between Qualitative, Quantitative research and mixed methods like Audiense.

Differences between qualitative and quantitative research, and why it is essential that you know this distinction when using Audiense Insights?

Qualitative Research

Qualitative Research is primarily exploratory research. It is used to gain an understanding of underlying reasons, opinions, and motivations. It provides insights into the problem or helps to develop ideas or hypotheses for potential quantitative research.

Qualitative Research is also used to uncover trends in thought and opinions, and dive deeper into the concern. Qualitative data collection methods vary, using unstructured or semi-structured techniques.

Some common methods include focus groups (group discussions), individual interviews, and participation/observations. The sample size is typically small, and respondents are selected to fulfil a given quota.

Quantitative Research

Quantitative research is used to quantify the concern by way of generating numerical data or data that can be transformed into usable statistics. It is used to quantify attitudes, opinions, behaviours, and other defined variables – and generalize results from a larger sample population.

Quantitative research uses measurable data to formulate facts and uncover patterns in research. Quantitative data collection methods are much more structured than Qualitative data collection methods.

This type of data collection methods include various forms of surveys – online surveys, paper surveys, mobile surveys and kiosk surveys, face-to-face interviews, telephone interviews, longitudinal studies, website interceptors, online polls, and systematic observations. 

Here's a simple look at the difference between qualitative and quantitative data:

  • The age of your car. (Quantitative)
  • The number of hairs on your knuckle. (Quantitative)
  • The softness of a cat. (Qualitative)
  • The colour of the sky. (Qualitative)
  • The number of pennies in your pocket. (Quantitative)

What methodology am I using with Audiense Insights?

Think of Audiense as if you were doing a survey with a number of a set of answers, that are the results of our Insights Report. By definition, when you use Audiense you are using a mixed research method given that it provides quantitative (ie: demographics, interests, influencers, etc)  and qualitative results (ie: content). Nevertheless, if you don’t follow a quantitative research design your research using Audiense will be interpreted as qualitative in the sense of exploratory research, to then inform better quantitative research.

 

An example of this would be:

Let’s say we want to understand the community of CEO’s of the UK.

I run an Audience Intelligence report on UK CEOs and let’s say Audiense finds 5,000 CEOs in the UK

At this point, I’m doing qualitative research in the sense of exploratory research. 

If you want to make it quantitative research, then you would need among other things included in the research design to quantify the total population to understand if the audience used for the report is significant enough.

Let’s say that I found in Google that the number of CEOs that are in the UK is around 200,000. Is the report generated by Audiense significant? 

Well, according to a sample size calculator, you would need only 384 with a margin error of 5% and confidence level of 95% (usually recommended values) and therefore your population of 5,000 would be significant.

 

The sample of a Quantitative research

A survey can only be truly valuable when it’s reliable and representative for your business. However, determining the ideal survey sample size and population can prove tricky. In other words, who will you be surveying and how many people? No idea?

Please find below for reference, but you can use http://www.raosoft.com/samplesize.html to adapt.

For example, largely trusted polls for something as difficult like elections, use a range of between 2000-10,000 depending the size of the country. http://www.pollofpolls.no/?cmd=Stortinget&do=snitt&yw=201902

Sources: 

https://www.snapsurveys.com/blog/qualitative-vs-quantitative-research/

https://journals.sagepub.com/doi/pdf/10.1177/1609406915624574